https://owenackermanportfolio.cargo.site Owen's Portfolio Tue, 16 Jun 2026 22:58:02 +0000 https://owenackermanportfolio.cargo.site en https://owenackermanportfolio.cargo.site/About-1 Thu, 16 Sep 2021 05:21:28 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/About-1 <img width="1736" height="1570" width_o="1736" height_o="1570" data-src="https://freight.cargo.site/t/original/i/25296dfe9adc033791bae5201fd6baa001994918c08f07ac09ca6b0bdd0fad31/ProfilePhoto.jpeg" data-mid="249520421" border="0" data-scale="30" src="https://freight.cargo.site/w/1000/i/25296dfe9adc033791bae5201fd6baa001994918c08f07ac09ca6b0bdd0fad31/ProfilePhoto.jpeg" /> Hello, my name is Owen Ackerman. I’m a Creative Technologist based in NYC and Berlin.&nbsp; I graduated as a Computer Engineering student with special interests in Math, Signal Processing, and Audio. Throughout my life, the most meaningful and passion driven projects have been in the intersection of tech and art. Whether it be designing electronic instruments from the lens of a musician and engineer, or as a creative technologist designing synchronized ribbon dancing robots for a kinetic installation, I connect to the world through my love of art and technology. I am a glass-half-full person and believe life is meant to be enjoyed. I try to keep things in perspective and remember life is what you put into it. I value human connection and try and ground myself in the now. Feel free to contact me, all inquiries are welcome! Personal Email: owenackerman1024@gmail.com ︎ https://owenackermanportfolio.cargo.site/FLOMOTION-1 Sat, 30 May 2026 16:51:50 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/FLOMOTION-1 .doc-wrap { font-family: inherit; max-width: 860px; margin: 0 auto; line-height: 1.6; } /* ── Tables ── */ .doc-wrap table { border-collapse: collapse !important; width: 100% !important; margin: 1.5em 0 !important; font-size: 0.88em !important; display: table !important; table-layout: auto !important; background: transparent !important; } .doc-wrap th, .doc-wrap td { border: 1px solid #888 !important; padding: 7px 11px !important; text-align: left !important; vertical-align: top !important; background: transparent !important; } .doc-wrap th { font-weight: 600 !important; background: transparent !important; } .doc-wrap tr { background: transparent !important; } /* ── Code blocks and ASCII art ── */ .doc-wrap pre { font-family: 'Source Code Pro', 'Courier New', Courier, monospace !important; white-space: pre !important; overflow-x: auto !important; background: rgba(128, 128, 128, 0.12) !important; border: 1px solid #888 !important; padding: 1em 1.2em !important; border-radius: 4px !important; font-size: 0.82em !important; line-height: 1.25 !important; margin: 1.2em 0 !important; letter-spacing: 0 !important; word-spacing: 0 !important; font-variant-ligatures: none !important; -webkit-font-smoothing: auto !important; } .doc-wrap pre code { font-family: 'Source Code Pro', 'Courier New', Courier, monospace !important; background: transparent !important; padding: 0 !important; font-size: inherit !important; white-space: pre !important; line-height: inherit !important; letter-spacing: 0 !important; word-spacing: 0 !important; } /* ── ASCII diagram font size (adjust this value) ── */ #ascii-system-overview, #ascii-system-overview code { font-size: 0.75em !important; } /* ── Inline code ── */ .doc-wrap p code, .doc-wrap li code, .doc-wrap td code, .doc-wrap th code { background: transparent !important; padding: 2px 5px !important; border-radius: 3px !important; font-size: 0.85em !important; font-family: 'Source Code Pro', 'Courier New', Courier, monospace !important; } /* ── Syntax highlighted code (Pandoc spans) ── */ .doc-wrap code.sourceCode { white-space: pre !important; } .doc-wrap .kw { color: #569cd6 !important; } .doc-wrap .st { color: #ce9178 !important; } .doc-wrap .co { color: #6a9955 !important; } .doc-wrap .op { color: inherit !important; } .doc-wrap .fl, .doc-wrap .dv { color: #b5cea8 !important; } .doc-wrap .va { color: #9cdcfe !important; } .doc-wrap .bu { color: #dcdcaa !important; } /* ── Image grid — tall cells, fixed 2-col ── */ .doc-wrap .img-grid { border: none !important; width: 100% !important; table-layout: fixed !important; } .doc-wrap .img-grid th { border: none !important; text-align: center !important; font-weight: 600 !important; padding: 4px 6px !important; } .doc-wrap .img-grid td { border: none !important; padding: 6px !important; text-align: center !important; vertical-align: top !important; width: 50% !important; } .doc-wrap .img-grid .img-square { width: 100% !important; overflow: hidden !important; display: block !important; position: relative !important; } .doc-wrap .img-grid .img-square img, .doc-wrap .img-grid .img-square figure, .doc-wrap .img-grid .img-square > * { width: 100% !important; height: auto !important; object-fit: cover !important; display: block !important; margin: 0 !important; } /* ── Blockquotes ── */ .doc-wrap blockquote { border-left: 3px solid #555 !important; margin: 1em 0 !important; padding: 0.5em 1em !important; color: #aaa !important; } /* ── Headings ── */ .doc-wrap h1 { font-size: 1.9em; margin-top: 0; } .doc-wrap h2 { font-size: 1.4em; margin-top: 2em; border-bottom: 1px solid #333; padding-bottom: 0.3em; } .doc-wrap h3 { font-size: 1.1em; margin-top: 1.6em; } .doc-wrap h4 { font-size: 1em !important; margin-top: 1.4em !important; color: inherit !important; } /* ── Scrollable wide tables ── */ .doc-wrap .table-scroll { display: block !important; overflow-x: auto !important; -webkit-overflow-scrolling: touch !important; width: 100% !important; } /* ── Misc ── */ .doc-wrap hr { border: none; border-top: 1px solid #333; margin: 2em 0; } .doc-wrap img { max-width: 100%; height: auto; } .doc-wrap ul, .doc-wrap ol { padding-left: 1.5em; } .doc-wrap li { margin-bottom: 0.3em; } Robotic Ribbons — FLOWMOTION A kinetic installation of 6 robotic arms, each animating a ribbon through coordinated motion and synchronized lighting. Commissioned by Florian Goerlitz for the Light Art Festival in Heidenheim, Germany. Designed, engineered, and built at MotionLab Berlin. Table of Contents Project Overview Motion Design &amp; Concept Mechanical Design Electronics Architecture Software Architecture Show Design: Motion &amp; Lighting Timecode Transportation &amp; Setup Lessons Learned &amp; Next Steps Credits 1. Project Overview The piece was inspired by synchronized ribbon dancers — the way a group of performers can move as a single organism, each ribbon tracing its own path through space while contributing to a shared visual field. FLOWMOTION translates that choreographic logic into a machine: six robotic arms, each carrying a ribbon, moving in spherical coordinates under a unified control system. FLOMOTION in a linear configuration in a castle at the Light Art Festival in Heidenheim, Germany. FLOMOTION in a circular configuration in a theatre at the Aux Actes Citoyens in Tomblaine, France. 2. Motion Design &amp; Concept 2.1 Starting Point — What Motion Do We Want? We started with understanding the types of circular and rhythmic motions people have used to control ribbons. How does the human arm work in coordination with a ribbon's natural movement? The design process began with an analysis of how humans dance with ribbons. We started to understand the relationship between how a human arm navigates a ribbon which then naturally flows through the air. We wanted the movement to be continuous, three-dimensional sweeps. The goal was to translate that quality into motorized motion: organic, wave-like, but also powerful enough to make sharp changes. 2.2 Identifying the Right Degrees of Freedom Early explorations considered several mechanical configurations, but a spherical two-motor design was chosen because it directly maps to the mathematics of smooth orbital motion and flow patterns. It also allowed for a robust configuration of powerful motors for controlled motion. The following animations were made in Desmos 3D to test what kind of motion was possible along a unit sphere using this spherical coordinate motor system. All of these animations were used by programming different functions onto the theta and phi angles. Rotation <img width="1420" height="1288" width_o="1420" height_o="1288" data-src="https://freight.cargo.site/t/original/i/3f8da39a0f6444826793695dc5f8d604c257a9af9c7d52e3ae9b79b39fc342cf/SphericalAnimationRotationGIF.gif" data-mid="249351203" border="0" src="https://freight.cargo.site/w/1000/i/3f8da39a0f6444826793695dc5f8d604c257a9af9c7d52e3ae9b79b39fc342cf/SphericalAnimationRotationGIF.gif" /> Figure 8 <img width="1276" height="1116" width_o="1276" height_o="1116" data-src="https://freight.cargo.site/t/original/i/8c027e497d5357d2eaa0481a5209cfc9d96d4e3db3a19af9f342c7f52b4b018c/SphericalAnimationFigure8GIF.gif" data-mid="249351201" border="0" data-scale="23" src="https://freight.cargo.site/w/1000/i/8c027e497d5357d2eaa0481a5209cfc9d96d4e3db3a19af9f342c7f52b4b018c/SphericalAnimationFigure8GIF.gif" /> High Frequency <img width="1370" height="1258" width_o="1370" height_o="1258" data-src="https://freight.cargo.site/t/original/i/d02bf926ca102d32ca0f7d19c8cff9b18208f72bc49a58f6fc7f5830c70b4501/SphericalAnimationHighFreqGIF.gif" data-mid="249351202" border="0" src="https://freight.cargo.site/w/1000/i/d02bf926ca102d32ca0f7d19c8cff9b18208f72bc49a58f6fc7f5830c70b4501/SphericalAnimationHighFreqGIF.gif" /> Complex Motion <img width="1370" height="1298" width_o="1370" height_o="1298" data-src="https://freight.cargo.site/t/original/i/6ba33bee230f0568771ef3cd7f9a0e8ec043240604e9155abafd933f2a9f75f4/SphericalAnimationCrazyGIF.gif" data-mid="249351200" border="0" src="https://freight.cargo.site/w/1000/i/6ba33bee230f0568771ef3cd7f9a0e8ec043240604e9155abafd933f2a9f75f4/SphericalAnimationCrazyGIF.gif" /> 2.3 Spherical Coordinate Model Each robot arm's position is defined by two angles: Theta (θ) — azimuthal rotation in the XZ plane, around the Y axis. Range: 0–360°, continuous and wrapping. Controlled by velocity (rotations per second), driving a stepper motor at the corresponding pulse rate. Phi (φ) — elevation from Y+ (straight up). Range: −135° to +135°. Controlled by direct angle, sent as a PWM command to the servo. Y+ = phi 0° (arm pointing straight up) XZ plane = phi 90° (arm horizontal) Y- = phi ±135° (servo hardware limit) Theta: azimuth in XZ plane, 0–360°, wraps continuously Cartesian mapping: y = cos(phi) x = sin(phi) * sin(theta) z = sin(phi) * cos(theta) theta = atan2(x, z) The choice of velocity control for theta (rather than position) was deliberate: it allows the stepper to spin continuously without needing to track absolute position, and makes wave behaviors — where robots rotate at slightly different speeds or with phase offsets — natural to express. <img width="1322" height="1279" width_o="1322" height_o="1279" data-src="https://freight.cargo.site/t/original/i/43515a1f0e61f16e344ffccecbf33e55ae3dd4fecbf70ae3e44893221c9a458f/RobotArmCoordinateSystem.jpg" data-mid="249351195" border="0" data-scale="51" src="https://freight.cargo.site/w/1000/i/43515a1f0e61f16e344ffccecbf33e55ae3dd4fecbf70ae3e44893221c9a458f/RobotArmCoordinateSystem.jpg" /> Spherical coordinate system diagram 2.4 TouchDesigner Motion Controller Preview Exploration of TouchDesigner UI for motion controller. Constant velocity on theta motor, sine wave placed on phi motor with variable parameters. In the following video I explore the different patterns that can emerge from altering the sine wave parameters for each of the robots. 3. Mechanical Design 3.1 Robot Arm Structure Each robot consists of: A stepper motor (theta axis) — continuous azimuthal rotation, driven by a DM860 driver at 800 pulses/revolution A servo motor (phi axis) — 270° range, 25.2V supply, direct angle control A rigid arm of length 1 m — 12mm wide hollow aluminum tubing A ribbon attachment point at the tip with bearing for natural rotation during flight A proximity sensor to establish a known reference position (theta = 315°) on startup — sensor signal voltage-divided from 25.2V to ~4.2V via a 1MΩ / 200kΩ divider for safe Arduino input Note on ribbon behavior: at low speed near phi ≈ 0° (arm pointing straight up), the ribbon can become caught around the arm. This is a known mechanical constraint that shaped how behaviors approach the vertical. <img width="959" height="1286" width_o="959" height_o="1286" data-src="https://freight.cargo.site/t/original/i/ed6d37f0f9203c95ab0154a4ddc86d1ffe81fdccdb36d3be4df63a56796c847a/RobotDesignSketchCrop.jpg" data-mid="249471966" border="0" data-scale="98" src="https://freight.cargo.site/w/959/i/ed6d37f0f9203c95ab0154a4ddc86d1ffe81fdccdb36d3be4df63a56796c847a/RobotDesignSketchCrop.jpg" />Design Sketch <img width="602" height="936" width_o="602" height_o="936" data-src="https://freight.cargo.site/t/original/i/27abd11cc89793eb5acb11d551054fb890d2b5bdb3024c3cd40b0b18694c17e3/CutRobotImage2.PNG" data-mid="249353164" border="0" data-scale="85" src="https://freight.cargo.site/w/602/i/27abd11cc89793eb5acb11d551054fb890d2b5bdb3024c3cd40b0b18694c17e3/CutRobotImage2.PNG" />Mechanism <img width="3503" height="4668" width_o="3503" height_o="4668" data-src="https://freight.cargo.site/t/original/i/49a352d0887b9cce781f7d9d4fb6755e2e3d4f544e25fb5df0c75482323c8953/IMG_0200.jpeg" data-mid="249471077" border="0" data-scale="97" src="https://freight.cargo.site/w/1000/i/49a352d0887b9cce781f7d9d4fb6755e2e3d4f544e25fb5df0c75482323c8953/IMG_0200.jpeg" />Mechanism Innards <img width="4284" height="5712" width_o="4284" height_o="5712" data-src="https://freight.cargo.site/t/original/i/51452f86048a37fe9b3428f7c8582fca12c6f4af79596a4d91355840b8e86cc9/RobotGroupPhoto.jpeg" data-mid="249351197" border="0" data-scale="97" src="https://freight.cargo.site/w/1000/i/51452f86048a37fe9b3428f7c8582fca12c6f4af79596a4d91355840b8e86cc9/RobotGroupPhoto.jpeg" />Full Length Robots 3.2 Physical Parts List (Per Robot) Part Specification Notes Stepper motor NEMA 34, 8.5 Nm holding torque Theta axis Stepper driver DM860 800 ppr DIP switch setting required Servo motor 270° servo, 25.2V supply Phi axis, −135° to +135° Arm 1 m aluminum rod, 12 mm diameter, 2 mm wall thickness Homing sensor Metal proximity sensor 25.2V supply, signal divided to ~4.2V Power module 60V stepper supply + 25.2V DC-DC buck One per robot Ribbon 75 mm width, 4 m length Mounting hardware M6 rods and nuts 3.4 Design Files [TODO: Link CAD files, 3D print files, and laser cut files.] 4. Electronics System Architecture 4.1 System Overview The system starts with TouchDesigner running on a MiniPC as the central brain where the ribbon motion is designed and sequenced. TD sends out live motor values via serial to an Arduino which connects to each robot's power box. This power box holds a voltage transformer and a motor driver which powers each robot. Each robot also sends back sensor data to the Arduino to monitor its position. <img width="2316" height="1138" width_o="2316" height_o="1138" data-src="https://freight.cargo.site/t/original/i/8119c22f2a86d83f2f4ef3f5eeacbff5be593ed71ff281cc42cef4876640a7a3/RobotWiringDiagram.jpg" data-mid="249351199" border="0" data-scale="68" src="https://freight.cargo.site/w/1000/i/8119c22f2a86d83f2f4ef3f5eeacbff5be593ed71ff281cc42cef4876640a7a3/RobotWiringDiagram.jpg" /> Hardware and electronics overview diagram The electronics form a two-tier hierarchy: a central control computer runs all show logic and communicates to a single Arduino, which fans out to six robot nodes via individual Ethernet links. Lighting is handled by a dedicated ESP32 DMX controller on the same network. <img width="1198" height="476" width_o="1198" height_o="476" data-src="https://freight.cargo.site/t/original/i/213054e07d500f1f2447656d9a1f10ddff3874fd9e197ee9377977111eb9fd4f/image.png" data-mid="249472061" border="0" data-scale="69" src="https://freight.cargo.site/w/1000/i/213054e07d500f1f2447656d9a1f10ddff3874fd9e197ee9377977111eb9fd4f/image.png" /> 4.2 Control Computer → Arduino (Serial) TouchDesigner communicates with the Arduino over USB serial. Per-robot data sent each frame: Data Encoding Notes Theta velocity (-theta_velocity × 800) + 100000 100000 = stopped; &gt;100000 = forward; &lt;100000 = reverse Phi angle Degrees, range −135 to +125 Direct servo angle LED color R, G, B values Per-robot RGB fixture The offset encoding for theta means the Arduino receives a single unsigned integer that encodes both direction and speed — values above 100000 are forward rotation, values below are reverse, and the magnitude of the offset is the pulse rate. The Arduino sends 'HOMED' over serial when the homing sequence completes. 4.3 Arduino → Robot Nodes (Ethernet) Each of the six robots has its own dedicated Ethernet connection from the Arduino, allowing independent simultaneous command delivery. The Ethernet carries two data lines to the stepper motor, one to the servo, and one back from the homing sensor. Ethernet was chosen for its twisted-pair wiring, which rejects noise and keeps signal integrity over the cable runs between the central box and each robot. 4.4 Motor Control Stepper Motor — Theta Axis (DM860 Driver) The DM860 accepts standard PUL / DIR / ENA signals with built-in optocouplers. Critical: the Arduino ground must be fully isolated from the 60V system to protect the DM860 optocouplers. SignalNotes PULPulse input — rate sets velocity DIRDirection ENAEnable (active low) Resolution800 pulses/revolution (DM860 DIP switch) Supply voltage60V Servo Motor — Phi Axis ParameterValue ControlStandard PWM Supply voltage25.2V (DC-DC buck, non-isolated from 60V rail) Range−135° to +135° Homing Sensor ParameterValue Supply voltage25.2V Signal conditioningVoltage divider: 1MΩ + 200kΩ → ~4.2V at Arduino input Homing referencetheta = 315° 4.5 Power Architecture Each robot has its own dedicated power module, isolating load and simplifying fault isolation. RailVoltagePowersNotes Main supply60VDM860 stepper driver DC-DC buck25.2VServo motor, homing sensorNon-isolated from 60V rail Logic supply5V isolatedArduino Mega 2560Must be fully isolated from 60V 4.6 Lighting — ESP32 DMX Controller Each robot has one RGB DMX fixture (3 channels: R, G, B). A dedicated ESP32 receives Art-Net UDP from TouchDesigner and outputs DMX512 via a MAX485 RS-485 transceiver. ComponentDetail MicrocontrollerESP32 LibraryDmx_ESP32 Protocol inArt-Net (UDP) Protocol outDMX512 via MAX485 transceiver Channels used18 total (6 robots × 3 RGB channels) The Dmx_ESP32 library was adopted after resolving persistent DMX break-timing issues with the initial implementation, which caused fixture flicker and dropout. Correct break timing is handled automatically by the library. 5. Software Architecture 5.1 Stack Overview LayerTool / Language Show control &amp; orchestrationTouchDesigner (Python extensions) Motion mathPython (spherical coordinates, phase accumulators) Serial communicationTouchDesigner Serial DAT Microcontroller firmwareArduino C++ (Mega 2560) Lighting outputArt-Net DAT → ESP32 → DMX512 Inter-machine communication for hand controlOSC over direct Ethernet 5.2 TouchDesigner Node Structure /project1 /controller_comp Base COMP — RobotControllerEXT /sequencer_comp Base COMP — ShowSequencerEXT /recorder_comp Base COMP — MotionRecorderEXT /Robot1 .../Robot6 Base COMP — RobotEXT const_robot Constant CHOP — motor output values for each robot The Execute DAT calls all three extensions in order every frame: op('sequencer_comp').ext.ShowSequencerEXT.Update() # sets params first op('controller_comp').ext.RobotControllerEXT.Update() # computes motion op('recorder_comp').ext.MotionRecorderEXT.Update() # captures state last 5.3 RobotEXT — Per-Robot State Container RobotEXT is a pure data container — one instance per robot arm. It tracks current position, velocity, and hardware limits, and writes motor commands to a Constant CHOP each frame. State AttributeUnitDefault thetadegrees0.0 (range 0–360°) phidegrees90.0 (range −135° to +135°) theta_velocityrps0.0 phi_velocitydeg/s0.0 Hardware Limits LimitDefaultNotes pulses_per_revolution800Must match DM860 DIP switch max_theta_velocity1.5 rps max_phi_velocity540.0 deg/sEquivalent to 1.5 rps max_theta_acceleration2.3 rps/s0 = unlimited max_phi_acceleration1.0 deg/s²0 = unlimited CHOP Output Each frame, PushToCHOP() writes three values to the robot's Constant CHOP: const0value = theta (deg) const1value = phi (deg) const2value = (-theta_velocity × 800) + 100000 100000 = stopped &gt; 100000 = forward rotation &lt; 100000 = reverse rotation Key Methods SetState(theta, phi, ledMatrix, dt=None) # If dt &gt; 0: derives velocity from delta/dt, applies accel clamping. # If dt is None or 0: snaps to position, zeroes velocity. Halt() # Zeros velocity and pushes to CHOP. # Always use this from outside — never assign r.theta_velocity directly # (TD extension promotion does not intercept attribute assignment) 5.4 RobotControllerEXT — Motion Orchestration RobotControllerEXT owns all motion logic: behavior evaluation, weighted blending, smooth transitions, stop/resume ramps, and the homing sequence. Update Loop (Every Frame) 1. Skip if dt &lt; 0.001 (double-cook guard) 2. Read rotation axis from CHOP if quaternion behavior active 3. Advance homing state machine if running 4. If paused: return early 5. Scale effective_dt by stop/resume ramp factor 6. Accumulate internal show time 7. Exponential-lag smooth all behavior parameters (τ ≈ 1/6 s) 8. Evaluate all active behaviors; blend by normalized weight 9. Apply blended states to each RobotEXT via SetState + PushToCHOP Behavior System Multiple behaviors can run simultaneously. Each has an independent weight and parameters that are exponentially smoothed each frame before evaluation: alpha = 1 - exp(-6.0 * dt) smoothed = smoothed + (target - smoothed) * alpha Blending is normalized weighted: if sine has weight 0.7 and wave has weight 0.3, the output is a 70/30 blend of what each behavior would produce. This enables smooth crossfades with no discontinuities. Built-in Behaviors BehaviorDescription sineTheta at constant velocity; phi oscillates sinusoidally with per-robot phase offsets waveBoth theta and phi oscillate sinusoidally from absolute show time noiseSame as wave at higher frequency, smaller amplitude — good for subtle organic perturbation circularAll robots trace circles in a tilted plane using per-robot angle accumulators quaternionRotates arm vectors around an arbitrary 3D axis (Rodrigues' formula); supports live CHOP input for the rotation axis circle_zyTraces a circle on the unit sphere in a plane offset from the ZY axis figure8Lissajous figure-8: theta at frequency f, phi at 2f figure9Inverse Lissajous: theta at 2f, phi at f flipBinary phi toggle — all robots snap to ±135° stepper_speed_controlTheta spins continuously; phi set directly with cascading delay ripple between robots stepper_direct_controlDirect position control for both axes with independent cascading delays Behaviors involving continuous accumulation (sine, circular, figure8, etc.) maintain per-robot phase accumulators so parameter changes — e.g. changing frequency mid-show — are seamless rather than causing a position jump. Fade System ctrl.fadeTo('wave', duration=2.0) Transitions use cubic ease-in-out interpolation. For sine and circular, the endpoint is predicted duration seconds ahead, so the incoming behavior lands without a visible seam. On completion, all other weights are zeroed and the target is set to 1.0. Stop / Resume ctrl.stop() # Smooth decel over decel_duration (default 0.5s) ctrl.resume() # Smooth accel back up ctrl.hardStop() # Instant — zeroes all velocities immediately Stop and resume work by scaling effective_dt over the ramp window, so velocity reaches zero naturally through the same acceleration clamping used during normal motion. 5.5 Homing Sequence On startup (or whenever the installation needs to re-reference), homing runs through a four-state machine: None → 'decelling' → 'waiting' → 'resuming' → None All robots decelerate to a stop Controller pulses a configurable trigger op to activate the Arduino homing routine Each robot drives toward its homing sensor; on contact, theta is zeroed and the reference is set to 315° Arduino sends 'HOMED' over serial when all robots are referenced Controller resumes motion, restoring each robot's saved phi value ctrl.startHoming( trigger_op = 'button_home', trigger_par = 'Pulse', serial_dat = 'serial1', done_string = 'HOMED' ) 5.6 MotionRecorderEXT — Live Motion Capture The recorder captures live robot states into named clips at a configurable sample rate (default 30fps), then registers each clip as a dynamic behavior on the controller — meaning recorded motion can be weighted, blended, and faded identically to any built-in behavior. rec.startRecording('take_1') # begin capture rec.stopRecording() # finalize and register on controller ctrl.fadeTo('take_1', 2.0) # crossfade into recorded motion rec.setClipSpeed('take_1', 0.5) # half speed playback rec.setClipLoop('take_1', False) # one-shot (holds last frame) rec.saveClips('show/clips.json') # persist to disk rec.loadClips('show/clips.json') # restore and re-register on load This was particularly useful during choreography development — interesting moments discovered through live manipulation could be captured immediately and played back precisely. 5.7 ShowSequencerEXT — Timecoded Show Playback The show is authored as a Table DAT — one row per segment — which the sequencer reads to drive the controller over time. The sequencer must update before the controller each frame so parameters land in the same frame they're intended for. Table Format time_start duration behavior blend_start blend_end params_start params_end 0.010.0sine theta_velocity=0.1 bias_phi=-90 theta_velocity=0.3 bias_phi=-45 10.04.0sine/wave0.01.0 theta_velocity=0.2 14.08.0figure8 frequency=0.25 amplitude_theta=60 frequency=0.5 amplitude_theta=30 behavior — single name (sine) or crossfade pair (sine/wave); in crossfade mode, blend_start/blend_end control the weight of the second behavior across the segment duration params_start / params_end — space-separated key=value pairs; the sequencer interpolates linearly between them over duration seconds The sequencer fully owns weight state during playback — it zeros all behavior weights every frame Segments are sorted by time_start automatically on load Playback Controls seq.loadFromDAT('sequencer_table') seq.play() # start / resume seq.pause() # freeze; controller holds current state seq.seek(30.0) # jump to 30s; immediately applies that segment's state seq.setLoop(True) seq.seq_time # current playhead position in seconds (read-only) 5.8 Key TouchDesigner Implementation Notes These patterns were non-obvious and important to get right: Frame-persistent state — scriptOp.store() / fetch() used for values that must survive TD cook cycles; instance variables alone are not reliable Absolute time — absTime.seconds used for show timing; me.time.seconds resets on component resets and is unsuitable for a running installation Extension promotion — methods on RobotEXT are promoted to the operator level (r.Halt() works), but attribute assignment (r.theta_velocity = x) does not go through the extension — always use setter methods Double-cook guard — TD fires Execute DATs multiple times per frame with dt≈0; the guard if dt &lt; 0.001: return prevents the second cook from zeroing velocities 5.9 Source Files FileRole DATS/RobotEXT.pyPer-robot state container and CHOP output DATS/RobotControllerEXT.pyAll motion logic: behaviors, blending, fading, stop/resume, homing DATS/MotionRecorderEXT.pyRecords robot motion into named clips; registers clips as behaviors DATS/ShowSequencerEXT.pyTimecoded show: Table DAT-driven parameter sequences 6. Show Design: Motion &amp; Lighting Timecode 6.1 Approach Both motion and lighting are driven from a single timecoded Table DAT sequence in TouchDesigner, read by ShowSequencerEXT. The sequencer owns a single internal clock and drives RobotControllerEXT with interpolated behavior parameters each frame — including both motor targets and LED colors. Because everything shares one clock and one update loop, motion and lighting are structurally guaranteed to stay in sync across playback, seek, pause, and loop operations. 6.2 Motion Authoring Motion is authored by writing segments into the sequencer_table Table DAT. Each segment specifies which behavior is active, its parameters at the start and end of the segment (with linear interpolation between), and optionally a crossfade to a second behavior. time_start duration behavior params_start params_end 0.08.0sine theta_velocity=0.1 bias_phi=-90 theta_velocity=0.2 bias_phi=-60 8.04.0sine/wave theta_velocity=0.2 12.010.0wave frequency_phi=0.5 amplitude_phi=30 frequency_phi=1.5 amplitude_phi=60 22.06.0figure8 frequency=0.25 amplitude_theta=60 frequency=0.5 amplitude_theta=30 Certain moments in the show were developed through live performance — moving the robots in real time through parameter manipulation — and captured using MotionRecorderEXT. These clips were then incorporated into the sequence as named behaviors alongside the procedural ones. 6.3 Lighting Each robot has one RGB DMX fixture, addressed as 3 consecutive DMX channels. Lighting is controlled by the same Table DAT / ShowSequencer system as motion — there is no separate lighting timeline. Every behavior function returns a led: [r, g, b] value per robot alongside theta and phi. These values flow through the same normalized weighted blend as the motion state, so lighting crossfades automatically whenever behaviors crossfade. Lighting cues are authored directly in the sequencer_table using the same params_start / params_end syntax: time_start duration behavior params_start params_end 0.08.0sine led_r=0 led_g=50 led_b=255 led_r=0 led_g=100 led_b=255 8.04.0wave led_r=255 led_g=80 led_b=0 led_r=255 led_g=255 led_b=0 6.4 Show Sections The show was built through a sequence of timecoded commands. In this short example, we first start the show by cutting the lights and homing all of the motors. Then the music starts and robot one shoots to life along with its lights, then after 5 seconds, robot 2 joins. We did this for about 300 different timecodes along a 7 minute song to create a choreographed light-controlled show. TimeSectionMotion BehaviorLightingNotes 0:00Startup / HomingAll robots home at theta=315°DarkSilent calibration 0:05Song beginsOnly Robot 1 movesOnly Robot 1 lights up 0:10Robot 2 joinsRobot 2 light joins …~300 timecoded cues over 7 minutes 7. Transportation &amp; Setup The installation was transported in custom shipping containers.&nbsp;<img width="4284" height="5712" width_o="4284" height_o="5712" data-src="https://freight.cargo.site/t/original/i/e404c859bf87cee0e544082c9e3200b1eb640c63d38423e3168a5fe11a42d7f6/RobotsInPackaging.jpeg" data-mid="249351198" border="0" data-scale="36" src="https://freight.cargo.site/w/1000/i/e404c859bf87cee0e544082c9e3200b1eb640c63d38423e3168a5fe11a42d7f6/RobotsInPackaging.jpeg" /><img width="4284" height="5712" width_o="4284" height_o="5712" data-src="https://freight.cargo.site/t/original/i/6d7ca17e5bb9ac62fd1e58ad464859dbba61a4cead9ddc93e26bec25831d40be/IMG_1426.jpeg" data-mid="249474186" border="0" data-scale="36" src="https://freight.cargo.site/w/1000/i/6d7ca17e5bb9ac62fd1e58ad464859dbba61a4cead9ddc93e26bec25831d40be/IMG_1426.jpeg" /><img width="5712" height="4284" width_o="5712" height_o="4284" data-src="https://freight.cargo.site/t/original/i/b1f2aab5ed8144bf5e02e2427185edda4061c7f50f365cc335e21333a58e1b28/IMG_1430.jpeg" data-mid="249474185" border="0" data-scale="58" src="https://freight.cargo.site/w/1000/i/b1f2aab5ed8144bf5e02e2427185edda4061c7f50f365cc335e21333a58e1b28/IMG_1430.jpeg" /> 8. Lessons Learned &amp; Next Steps This project was a full end-to-end build under real installation pressure — hardware, electronics, firmware, and software all developed in parallel against a hard ship date. Below are the post-mortems from each layer. 8.1 Hardware Vulnerability: stepper-to-servo coupling screw The most consequential mechanical issue was the M_ screw connecting the 12mm stepper motor axle into the servo motor flange mount. Under repeated rotation, this screw would occasionally snap. When it did, the servo motor wires became the only thing supporting the rotational load — causing them to twist, short, and in several cases blow out digital pins on the Arduino. The root cause is mechanical: without a tight interference fit between the axle and the flange bore, all rotational strain concentrates on the fastener. The correct fix is proper milling of both the flange and the axle to achieve a tight press or keyed fit that transfers torque through the metal geometry rather than the screw. This was identified during the build and during the installation we drilled through and expanded the holes, filling it with a larger bolt. This came after failures that resulted in several hours of repair time. Next time: prioritize machined fits for any joint that sees continuous cyclic load. A screw should be a safety fastener, not the primary torque path. Wiring to the servo motor Because the servo wires travel a very short, constrained distance, they were extremely difficult to repair after the coupling screw broke — the failure cascade (screw snaps → wires take load → wires rip or short) often happened faster than it could be caught, and repair required significant disassembly. Next time: use breakaway connectors — connectors designed to release under tension — on the servo wiring. If the coupling fails, the connector separates cleanly before the wires are damaged or a short reaches the electronics. In addition, if the first hardware fastener issue was fixed, this issue wouldn't be a problem. Takeaway: beware of cascading failures. 8.2 Electronics No per-robot isolation The current architecture has all six robots sharing data lines back to a single Arduino with no electrical isolation between them. When a robot node fails — especially where a mechanical failure causes a short or voltage spike — the fault can propagate up the data line and damage the Arduino, potentially taking down the entire installation. Next time: add optocouplers on every data line between the Arduino and the robot nodes. An optocoupler breaks the electrical path entirely — a short or voltage spike on the robot side can't reach the Arduino. The failure mode becomes "that robot stops working" rather than "the whole system goes down." Takeaway: beware of cascading failures. 8.3 Software Developing inside a larger TD network without full context The Python extension classes (RobotEXT, RobotControllerEXT, ShowSequencerEXT, MotionRecorderEXT) were developed using Claude Code, which worked well for the self-contained logic. The difficulty was that a significant amount of the TouchDesigner network — the wiring, the CHOPs that feed into the extensions, the DATs that read out of them — existed outside the codebase and therefore outside Claude's context. Claude Code couldn't see or reason about the full system, which meant bugs at the boundary between the Python extensions and the TD network were harder to catch and took longer to debug. Next time: have Claude Code implement unit tests for every extension class that simulate the TD environment — mocking absTime, scriptOp.store/fetch, CHOP reads and writes — and verify that each public method produces the exact expected output. This would have caught boundary bugs much earlier, shortened the debugging cycle considerably, and produced a more robust system overall. Closing the loop on AI-assisted development requires giving the AI a way to verify its own work against the real integration surface. 9. Credits RoleName Concept, artistic direction, design, fabricationFlorian Goerlitz Artistic direction, design, engineering, fabricationOwen Ackerman Development studioMotionLab Berlin Exhibitions: Light Art Festival, Heidenheim, Germany — 4/24–5/2/2026 Aux Actes Citoyens Theatre Festival, Tomblaine, France — 5/9–16/2026 Documentation last updated: 6/15/2026 https://owenackermanportfolio.cargo.site/Interactive-Ribbons-1 Tue, 16 Jun 2026 18:01:07 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Interactive-Ribbons-1 Interactive Ribbons In this project, I made a large spiraling ribbon driven by a large joystick. As you push and pull the joystick it drives a motor clockwise or counter-clockwise depending on the joystick position. This effect gives you the illusion that you’re controlling this spiraling ribbon with your hand. Controlling the intensity of wind pushing into your face.&nbsp; In this video I give a simple explanation of the project. An accelerometer is inside the joystick which is read by an esp32 which sends information to a motor driver. The x axis of the accelerometer determines the position and speed of the motor which drives the ribbon.&nbsp; https://owenackermanportfolio.cargo.site/Circular-Ribbons-1 Tue, 16 Jun 2026 22:58:02 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Circular-Ribbons-1 Circular Ribbons This installation consists of 6 ribbons aranged in a circle driven by synchronized stepper motors. In addition they were projection mapped onto for the Light Art Festival in Germany. https://owenackermanportfolio.cargo.site/Project-Soundscape-1 Wed, 07 May 2025 17:47:52 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Project-Soundscape-1 Project Soundscape was a year long research project to create a novel spatial audio system aimed at optimizing virtual source localization for a single user. After I convinced Bose to sponsor the project, I found 4 other engineers to help out with the software integration of the project while I worked on the Acoustic/DSP algorithm. Below You can find the overview project explanation in the poster paper below as well as the final written report for this project. Additionally I created a binaural video explanation of the project recorded using a Neumann KU 100 dummy head microphone. &nbsp; <img width="1936" height="1284" width_o="1936" height_o="1284" data-src="https://freight.cargo.site/t/original/i/cb70b9de32f5023df7e578ffd6aae3a70f9709f2658551495f58dfbec0479c50/Screenshot-2025-05-07-134205.png" data-mid="232908540" border="0" src="https://freight.cargo.site/w/1000/i/cb70b9de32f5023df7e578ffd6aae3a70f9709f2658551495f58dfbec0479c50/Screenshot-2025-05-07-134205.png" /> Final Report Link https://owenackermanportfolio.cargo.site/Machine-Learning-Transfer-Function-Prediction-1 Wed, 07 May 2025 03:18:08 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Machine-Learning-Transfer-Function-Prediction-1 <img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdMSWEXtwQXWXiFaAvEdkLjz8BFihFCU2f8mUbCyP8cofRQyqtne7kHu-lIZpxdjbxn4gno3kXGoAbIVIKP6-p691NjqDOF_xBSub5lKTr0j21EEbbj0Qy66_p9D8VS8lpEqhYLvg?key=k_qz4XlqE9162ZgcYais4w" width="624" height="851" style="width: 624px; height: 851px;"> https://owenackermanportfolio.cargo.site/Sound-Field-Synthesis-Exploration Tue, 19 Nov 2024 01:37:48 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Sound-Field-Synthesis-Exploration A mathematical exploration into Sound Field Synthesis. I created a set of notes from my personal exploration of SFS and created a python script that generates WFS animations. Here are some of the animations, the python script can be downloaded here. My math derivations and notes can be found below the animations. <img width="600" height="570" width_o="600" height_o="570" data-src="https://freight.cargo.site/t/original/i/2fecaf0695642bd6aded5503c260a53414a322eefc20a7f590b31b5578a5d2c2/WFSdoubleSource2-ezgif.com-video-to-gif-converter.gif" data-mid="222012595" border="0" data-scale="100" src="https://freight.cargo.site/w/600/i/2fecaf0695642bd6aded5503c260a53414a322eefc20a7f590b31b5578a5d2c2/WFSdoubleSource2-ezgif.com-video-to-gif-converter.gif" /> <img width="600" height="573" width_o="600" height_o="573" data-src="https://freight.cargo.site/t/original/i/c6f2e5600085e0acb5d1a049056cb2db149f119d8c2c004fe2bbdb138ac0dcd4/Figure12024-11-1820-16-44-ezgif.com-video-to-gif-converter.gif" data-mid="222012598" border="0" data-scale="100" src="https://freight.cargo.site/w/600/i/c6f2e5600085e0acb5d1a049056cb2db149f119d8c2c004fe2bbdb138ac0dcd4/Figure12024-11-1820-16-44-ezgif.com-video-to-gif-converter.gif" /> <img width="600" height="578" width_o="600" height_o="578" data-src="https://freight.cargo.site/t/original/i/bb90cb72e720f39eec80ea6cd1c455d98e3d8c91ef4328eaf88ab9d0bcdcb2eb/WFSdoulbeSource1-ezgif.com-video-to-gif-converter.gif" data-mid="222012596" border="0" data-scale="98" src="https://freight.cargo.site/w/600/i/bb90cb72e720f39eec80ea6cd1c455d98e3d8c91ef4328eaf88ab9d0bcdcb2eb/WFSdoulbeSource1-ezgif.com-video-to-gif-converter.gif" /><img width="600" height="577" width_o="600" height_o="577" data-src="https://freight.cargo.site/t/original/i/c40c108d6326a952f20857ab35968c980faed12b2b0c0704e8f621d7e5626a52/ezgif.com-video-to-gif-converter.gif" data-mid="222012683" border="0" data-scale="100" src="https://freight.cargo.site/w/600/i/c40c108d6326a952f20857ab35968c980faed12b2b0c0704e8f621d7e5626a52/ezgif.com-video-to-gif-converter.gif" /> Notes: <img width="1668" height="2154" width_o="1668" height_o="2154" data-src="https://freight.cargo.site/t/original/i/c9506eab7df7436eb6610d29c4be8ac9d0a17ab0765f545e1ad6baca01b54ec1/Wave-Field-Synthesis-3.jpg" data-mid="222012584" border="0" src="https://freight.cargo.site/w/1000/i/c9506eab7df7436eb6610d29c4be8ac9d0a17ab0765f545e1ad6baca01b54ec1/Wave-Field-Synthesis-3.jpg" /><img width="1668" height="2154" width_o="1668" height_o="2154" data-src="https://freight.cargo.site/t/original/i/4684e9e5fe5fb47d3f759154e92918c1dd8b1cb742ad98f5b75024662df6f07c/Wave-Field-Synthesis-4.jpg" data-mid="222012583" border="0" src="https://freight.cargo.site/w/1000/i/4684e9e5fe5fb47d3f759154e92918c1dd8b1cb742ad98f5b75024662df6f07c/Wave-Field-Synthesis-4.jpg" /> <img width="1668" height="2154" width_o="1668" height_o="2154" data-src="https://freight.cargo.site/t/original/i/915af9e16add95ad4405519ac4fe47f9a8e9bf13a66191210e109a6e01accef4/Wave-Field-Synthesis-5.jpg" data-mid="222012585" border="0" src="https://freight.cargo.site/w/1000/i/915af9e16add95ad4405519ac4fe47f9a8e9bf13a66191210e109a6e01accef4/Wave-Field-Synthesis-5.jpg" /><img width="1668" height="2154" width_o="1668" height_o="2154" data-src="https://freight.cargo.site/t/original/i/1e56a398a6fb9c67dc9873b61dc5137205ea74ab9406b5216d01af85a19874de/Wave-Field-Synthesis-6.jpg" data-mid="222012582" border="0" src="https://freight.cargo.site/w/1000/i/1e56a398a6fb9c67dc9873b61dc5137205ea74ab9406b5216d01af85a19874de/Wave-Field-Synthesis-6.jpg" /> https://owenackermanportfolio.cargo.site/Chimillian-1 Wed, 14 Aug 2024 15:26:49 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Chimillian-1 <img width="1460" height="1845" width_o="1460" height_o="1845" data-src="https://freight.cargo.site/t/original/i/4afc54d423aee76f692c25e0b5dd9b00994f5ce73ebd8b08656e04fc1ea66eea/ChimillianDocumentation.png" data-mid="216355517" border="0" data-scale="36" src="https://freight.cargo.site/w/1000/i/4afc54d423aee76f692c25e0b5dd9b00994f5ce73ebd8b08656e04fc1ea66eea/ChimillianDocumentation.png" /> https://owenackermanportfolio.cargo.site/Embedded-Medical-Devices-1 Sun, 24 Sep 2023 23:12:19 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Embedded-Medical-Devices-1 This past summer I worked in tandem with professor Joel Grodstein to design a new class at Tufts: Embedded Medical Devices. The main topics consist of programming in an embedded real time operating system ​(RTOS), and signal processing methods specifically for medical signals. A driving motivation of the course was to educate students on how an RTOS allows for reliable, precisely timed multi-tasking embedded devices. An RTOS provides the framework to schedule many tasks running at varying frequencies. This is helpful as many medical applications require lots of things to happen “concurrently” while typically only having a single core to work with. Over the summer, utilizing FreeRTOS I designed a heartbeat monitor. I implemented several types of real time filters such as differentiators, integrators, signal peak detectors, cascading biquads for highpass, lowpass and bandpass filters, and decision tree algorithms to classify a QRS wave. Simultaneously a buzzer is triggered on the heartbeat and a display is periodically updated to display the measured heart rate in BPM. In the course we used the many pitfalls I came up against in the summer project to create an RTOS “debug derby”, a style of lab where the students must debug a broken piece of code to better understand how RTOS’s work. We also teach basic real time signal processing, and PC based signal processing analysis. First we teach students how to design basic filters using python on their laptops so that they can play with different parameters and view the effects in the frequency domain in a nice GUI. After students have designed their filters, we teach them how to filter given real time constraints and explore the pitfalls that come outside the idealized world of python.&nbsp; We also teach more advanced signal processing ideas like wavelets which produce time localized frequency information, great for analyzing dynamic biological signals. Wavelets are one of my favorite signal processing topics and I was allowed to give a lecture on them! You can find the course webpage here. You can read more about the heartbeat detector designed using FREE RTOS and our signal processing labs here. Here is a live demo of the heartbeat monitor correctly classifying my heartbeat. My heart rate is shown on the display of the device below (Green circuit board). <img width="4032" height="3024" width_o="4032" height_o="3024" data-src="https://freight.cargo.site/t/original/i/4c3e7c6a6350f8399755f1e7be02f4ef67b49e9f24a4149c53f2d2882bbd3ec0/IMG_5858.jpg" data-mid="191945687" border="0" src="https://freight.cargo.site/w/1000/i/4c3e7c6a6350f8399755f1e7be02f4ef67b49e9f24a4149c53f2d2882bbd3ec0/IMG_5858.jpg" /> Here is an image of a scaleogram: a time, frequency, amplidude plot used to analyze dynamically changing signals. It’s the output of the continuous wavelet transform! <img width="1985" height="989" width_o="1985" height_o="989" data-src="https://freight.cargo.site/t/original/i/2f8c06720eecb62aadf628e45bc806e36364c3276b91e877eba0785d72de7db3/CWTpicture.png" data-mid="191945777" border="0" src="https://freight.cargo.site/w/1000/i/2f8c06720eecb62aadf628e45bc806e36364c3276b91e877eba0785d72de7db3/CWTpicture.png" /> https://owenackermanportfolio.cargo.site/Computer-Vision-1 Wed, 13 Sep 2023 22:35:09 +0000 Owen's Portfolio https://owenackermanportfolio.cargo.site/Computer-Vision-1 Here is a quick outline of some of the ideas that have influenced projects I’ve completed in the field of computer vision and machine learning. A full explanation and documentation of each project can be found on github here:&nbsp;GITHUB Feature matching, image warping and panoramas Feature matching is how we relate two images to each other. Through identifying several key features, like a corner or a dot, we can overlay two separate images of overlapping scenes by relating their key features. We can match features using SIFT, the scale invariant feature transform algorithm. First we can define a key feature as one with a large “contrast”, this means a large difference in the values of pixels, such as a border. We can filter out “bad” features as those which don’t have enough contrast, (using EigenValues to determine if there is enough contrast in enough directions, read harris corner detection). We then find the orientation of the feature so that we can compare it to other features. Once we have the key points of two images, we can filter for key points that are only shared between the 2 images. &nbsp; <img width="1162" height="427" width_o="1162" height_o="427" data-src="https://freight.cargo.site/t/original/i/79824eb30a6434b74b0fa645aae244cea8d4a5fe22fd8e6ee282337c5a92d973/FeatureMatching.png" data-mid="191519964" border="0" src="https://freight.cargo.site/w/1000/i/79824eb30a6434b74b0fa645aae244cea8d4a5fe22fd8e6ee282337c5a92d973/FeatureMatching.png" /> Now comes image warping. Usually when we take 2 pictures of the same scene, they’re at different angles, this is especially true for panoramic images. So in order to map 2 images onto each other, we define a homography, a 3d warping transformation of the image. Now, we solve for the optimal warping of one image to line up with the second. We do this with a least squares algorithm that optimizes for the number of overlapping key points between the two images. The result looks as follows. &nbsp; <img width="407" height="590" width_o="407" height_o="590" data-src="https://freight.cargo.site/t/original/i/40526bfd9f224ef9065b96e442745176bc79b552b3734ee69bbbbafb5b33dc6a/WarpingMatch.png" data-mid="191519965" border="0" data-scale="100" src="https://freight.cargo.site/w/407/i/40526bfd9f224ef9065b96e442745176bc79b552b3734ee69bbbbafb5b33dc6a/WarpingMatch.png" /> We can do this as an iterative process and stitch multiple images together! Here’s the result. <img width="1432" height="321" width_o="1432" height_o="321" data-src="https://freight.cargo.site/t/original/i/cbba3be1585681c5737108bbf30112493ba125a5ae64470b6096adeab5a45c0d/Panorama.png" data-mid="191519946" border="0" src="https://freight.cargo.site/w/1000/i/cbba3be1585681c5737108bbf30112493ba125a5ae64470b6096adeab5a45c0d/Panorama.png" /> TODO: Explanation of Facial recognition with Machine learning