1. Key terms
| Term | Definition |
|---|---|
| Sensor | A device that collects information from the world. Cameras see, microphones hear, LIDAR measures distances with lasers. |
| Compute | The chip / board where AI models run. Jetson, Raspberry Pi, or your Mac. |
| Actuator | Anything that makes a robot move or act. Servo motors rotate joints, wheels spin, grippers open and close. |
| Servo motor | A motor that rotates to a specific angle and holds. The primary actuator in robotic arms. |
| TOPS | Tera Operations Per Second. How fast an AI chip can process. Jetson Orin Nano = 67 TOPS. |
| CUDA | NVIDIA's programming platform for GPUs. Nearly all AI code runs on it. |
| LIDAR | Light Detection and Ranging. Shoots laser beams and measures bounce-back time to create 3D maps. |
| IMU | Inertial Measurement Unit. A small chip that measures tilt, rotation, and acceleration. |
| CSI | Camera Serial Interface. A flat ribbon cable connecting a camera directly to a board. Lower latency than USB. |
| DOF | Degrees of Freedom. How many independent axes a robot joint system can move. |
| PLA / PETG | Common 3D printing plastics. PLA cheaper and easier; PETG tougher and more heat-resistant. |
| Edge AI | Running AI models on local hardware instead of cloud servers. Low latency, private, no API costs. |
| FSR | Force Sensitive Resistor. A thin pad that changes electrical resistance when pressed. Used in gripper fingertips. |
| ESC | Electronic Speed Controller. Sits between a compute board and a brushless motor. |
2. The four columns
Every robot body is made of four types of components: sensors (eyes/ears/skin), compute (brain), actuators (muscles), structure (skeleton). The relationship is directional: sensors perceive, compute decides, actuators act, structure holds it all.
3. Sensors
How a robot perceives the world. Different sensors capture different information. The more and better sensors you add, the more compute power you need to process the data in real time.
Vision: RGB cameras
Two connection types. USB (UVC standard): plug into any USB port on any computer; works immediately with no drivers; good for learning. CSI cameras: flat ribbon cable directly into a Jetson or Raspberry Pi; lower latency than USB; used when speed matters.
| Product | Type | Resolution | Price |
|---|---|---|---|
| Logitech C920 / C922 | USB | 1080p | ~$50-70 |
| innomaker UVC Camera | USB | 1080p, 130° wide | ~$25-35 |
| Raspberry Pi Camera Module 3 | CSI | 12MP | ~$25 |
| Arducam (various models) | CSI / USB | Various | $15-80 |
Vision: depth cameras
Two technologies: stereo vision (two cameras side by side, like human eyes; works outdoors; RealSense D435, ZED) and time-of-flight (emits infrared light and measures bounce; more accurate at close range; struggles in bright sun).
| Product | Range | Best for | Price |
|---|---|---|---|
| Intel RealSense D435 | 0.2-10m | General robotics, wide FOV | $314 |
| Intel RealSense D435i | 0.2-10m | D435 + built-in IMU for motion tracking | $334 |
| Intel RealSense D405 | 0.07-0.5m | Close-range, gripper-mounted | $272 |
| Intel RealSense D455 | 0.4-6m | Longer range, outdoor capable | $419 |
| Stereolabs ZED 2i | 0.2-20m | Wide angle, IP66, AI-powered | ~$450+ |
| Stereolabs ZED X Nano | 0.03m+ | Wrist-mount, sub-mm accuracy | Pre-order |
Vision: LIDAR
Shoots thousands of laser beams per second in a spinning pattern, builds a "point cloud" 3D map. 2D LIDAR scans a single horizontal plane (good for indoor navigation, $99-600). 3D LIDAR scans multiple planes ($500-75K+, used in self-driving cars).
| Product | Type | Range | Price |
|---|---|---|---|
| Slamtec RPLIDAR A1 | 2D, 360° | 12m | $99 |
| Slamtec RPLIDAR A2 | 2D, 360° | 18m | $199-229 |
| Slamtec RPLIDAR A3 | 2D, 360° | 25m | $599 |
| Unitree 4D LIDAR L1 | 3D | Long range | Bundled with Go2 |
Audio: microphones and mic arrays
A single USB microphone captures voice commands. A microphone array detects direction and cancels background noise. ReSpeaker Mic Array v2.0 (~$60-80) is the standard for far-field voice on Jetson. Running Whisper (speech-to-text AI) locally on Jetson is medium-compute.
Motion: IMU and encoders
IMU (Inertial Measurement Unit): a small chip with accelerometers and gyroscopes. Tells the robot which way is up, if it is tilting, how fast it is moving. Essential for balancing humanoids and stabilizing drones. Often built into compute boards or depth cameras (the RealSense D435i includes one).
Encoders: built into servo motors. Report the exact angle of each joint back to the compute board. The SO-ARM101's STS3215 servos have 12-bit magnetic encoders (4,096 positions per rotation).
Touch: force sensors
FSR pads (Force Sensitive Resistors): thin flexible pads that change electrical resistance when pressed. Attached to gripper fingertips, they let the robot feel how hard it is squeezing. Without them, a robot cannot tell if it is about to crush a grape or drop a heavy mug. $10-50 per pad. Tactile sensor arrays are the more advanced version with a grid of sensing points; still mostly research.
Not in this list (specialized sensors)
Thermal / infrared cameras (heat vision), radar (used in cars alongside cameras and LIDAR), ultrasonic sensors (cheap parking-style distance), gas / chemical sensors, GPS modules, barometric pressure. Real but not needed for learning and first builds.
4. Compute
Compute is where the AI brain runs. It takes sensor data in, processes it through AI models, and sends commands to actuators. The compute board determines how many sensors run simultaneously and how complex the AI models can be.
The NVIDIA Jetson family (the dominant platform)
All Jetson boards run the same software (JetPack SDK). Code written on one works on any other. JetPack 6.2 (current production release) includes CUDA 12.6, TensorRT 10.3, cuDNN 9.3, Jetson Linux 36.4.3 (Linux Kernel 5.15, Ubuntu 22.04).
| Board | AI power | Memory | Handles | Price |
|---|---|---|---|---|
| Jetson Orin Nano Super (recommended) | 67 TOPS | 8GB | 2-4 cameras, local LLMs (8B at ~15 tok/s), real-time object detection | $249 |
| Jetson Orin NX | 100 TOPS | 8-16GB | Multi-model inference, complex robotics | $400-600 |
| Jetson AGX Orin | 275 TOPS | 32-64GB | Multiple large models simultaneously, commercial robots | $1-2K |
| Jetson Thor | 2,070 FP4 TFLOPS | 128GB | Foundation models (GR00T) on-device, humanoid robots | $1,999+ |
| Jetson T4000 | 1,200 FP4 TFLOPS | 64GB | Blackwell in smaller module. Announced CES 2026. | $1,999 (volume) |
What TOPS means in practice: the Orin Nano's 67 TOPS can process 2-4 camera streams at 30 fps while simultaneously running an object detection model (YOLO) and a local LLM (Llama 8B). Enough for a robotic arm, a security camera system, or a voice assistant. Step up the ladder when you need more.
Buy: Jetson Store | Orin Nano Super Dev Kit
Alternatives
| Board | AI power | Best for | Price |
|---|---|---|---|
| MacBook Pro (Apple Silicon) | ~38 TOPS Neural Engine | Development, testing, Ollama. Not a permanent robot brain. | Already owned |
| Raspberry Pi 5 + Hailo AI HAT+ | 13 TOPS | Single camera projects, entry-level edge AI | ~$120 |
| Google Coral USB Accelerator | 4 TOPS | Adding AI to any USB computer (TF Lite only) | ~$60 |
| IGX Platform (NVIDIA) | Same as Jetson Thor | Industrial / safety-certified (ISO 13849). Factories, hospitals. | Enterprise |
5. Actuators
How a robot acts on the world. Every physical movement (rotating a joint, spinning a wheel, opening a gripper, generating lift) is performed by an actuator. Actuators are surprisingly light on compute; the AI decision-making is the heavy part. Sending "rotate to 45 degrees" to a servo takes microseconds.
Servo motors (precise angle rotation)
Receives a command like "rotate to 135 degrees" and moves to that exact position. Holds against external force. Built-in encoder reports the current angle back to compute, creating a feedback loop. Servos can be daisy-chained: each motor has a unique ID, all share the same data cable. The SO-ARM101 daisy-chains 6 servos per arm.
| Product | Torque | Voltage | Price each | Used in |
|---|---|---|---|---|
| Feetech STS3215 | 19.5 kg/cm (7.4V) or 30 kg/cm (12V) | 7.4V or 12V | $15-29 | SO-ARM100 / 101 |
| ROBOTIS Dynamixel AX-12A | 15 kg/cm | 12V | ~$50 | Entry-level humanoid kits |
| ROBOTIS Dynamixel XL430 | 21 kg/cm | 12V | ~$50 | Replacement for AX-12A |
| ROBOTIS Dynamixel XM430 | 43 kg/cm | 12V | ~$115 | Research arms, professional kits |
Feetech vs Dynamixel: Feetech STS3215 costs $15-29 with open-source Python control. Dynamixel XM430 costs $115 with more torque and a professional SDK. The SO-ARM101 uses Feetech because the price / performance ratio is excellent for learning. Dynamixel is the industry standard for professional and research robots.
Feetech | ROBOTIS Dynamixel | WowRobo (STS3215)
Other actuator types
| Type | What it does | Used in | Price range |
|---|---|---|---|
| DC motors | Spin continuously at variable speed. Speed controlled by voltage. | Wheels (JetBot, JetRacer), conveyor belts, fans | $5-30 each |
| Stepper motors | Rotate in exact discrete steps (e.g., 1.8° per step). Precise without feedback sensors. | 3D printers, CNC machines, camera gimbals | $10-50 each |
| Linear actuators | Push / pull in a straight line. Like a motorized piston. | Industrial arms, adjustable platforms, lifts | $20-200 |
| Grippers | End effectors that open and close. Parallel jaw (two flat plates) or adaptive (conforms to shape). | End of any robotic arm. SO-ARM101 includes one. | $20-500 |
| Rotors / propellers | Spin at high RPM to generate lift. Quadcopters use 4 rotors. | Drones, quadcopters, fixed-wing UAVs | $10-50 each + ESC |
| Speakers | Sound is an actuator too. A robot that can talk back, beep, or play alerts. | Voice assistants, companion robots, Reachy Mini | $10-50 |
Not covered: pneumatic actuators (compressed-air, factory robots), hydraulic (fluid-powered, heavy construction), shape-memory alloys (experimental soft robotics), piezoelectric (tiny precise movements in surgical tools).
6. Structure
The physical frame that holds sensors, compute, and actuators together and gives the robot its form factor. Material depends on scale, environment, and budget.
| Material | What it is | Used in | Cost | Notes |
|---|---|---|---|---|
| 3D printed (PLA) | Polylactic Acid. Cheapest, most common 3D printing plastic. Biodegradable. | SO-ARM101 frames, custom mounts, prototypes | $5-50 | Easy to print. Brittle under stress. Not heat-resistant. |
| 3D printed (PETG) | Polyethylene Terephthalate Glycol. Tougher than PLA. | Parts needing more durability than PLA | $10-60 | More flexible, heat-resistant. Harder to print. |
| 3D printed (resin) | Photosensitive resin cured by UV light. Smoother surfaces, finer detail. | Waveshare SO-ARM kits use resin parts | $30-80 | More brittle than PLA but better tolerances. |
| Aluminum extrusion | T-slot aluminum profiles that bolt together like erector sets. | JetBot / JetRacer frames, workbenches, custom rigs | $20-100 | Strong, reusable, easy to modify. Standard sizes: 2020, 2040. |
| Metal chassis | Steel, aluminum, or titanium sheet / machined parts. | Vehicles (Tesla), industrial arms (FANUC, ABB) | $100-10K+ | Production-grade. Too expensive for learning. |
| Carbon fiber | Extremely light and rigid composite. | Drones (weight is critical for flight time), racing | $50-500 | Every gram matters when something flies. |
| Injection molded plastic | Plastic parts made in mass-production molds. | Consumer products (Reachy Mini body, phone cases) | N/A for hobby | Expensive molds, cheap per unit. Not for prototyping. |
7. How sensors connect to compute
This is the key hardware relationship. Actuators barely need compute power. Sensors drive the compute requirements because processing camera images and LIDAR point clouds takes millions of operations per frame.
| Sensor load | Example setup | Minimum compute |
|---|---|---|
| Light | 1 USB camera + motor encoders | Any (Mac, Raspberry Pi, or Jetson) |
| Medium | 2 cameras + 1 depth sensor (RealSense) | Jetson Orin Nano (67 TOPS) |
| Medium | 4 cameras at 1080p 30fps (security system) | Jetson Orin Nano to NX |
| Heavy | LIDAR + cameras + IMU (autonomous navigation) | Jetson Orin NX or AGX Orin |
| Heavy | Full humanoid sensor suite (all types) | Jetson Thor |
8. Manufacturer directory
Where to actually buy. Categorized by what they sell.
Compute boards
- NVIDIA Jetson Store (direct from NVIDIA)
- Seeed Studio (Jetson + sensors + kits)
- SparkFun (boards + components)
- Adafruit (boards + sensors + learning)
- Raspberry Pi (RPi + AI HAT+)
- Google Coral (Edge TPU)
Sensors
- Intel RealSense (depth cameras)
- Stereolabs ZED (depth + outdoor)
- Slamtec (LIDAR)
- Arducam (cameras of all kinds)
- Logitech (USB webcams)
Actuators (motors and servos)
- Feetech (STS3215, the SO-ARM standard)
- ROBOTIS Dynamixel (research-grade servos)
- WowRobo (Feetech distributor)
Kits and arms
- SO-ARM100 / 101 (open-source, ~$300 assembled)
- Reachy Mini ($299 Lite tethered, $449 Wireless with RPi 5; App Store launched May 6, 2026 with 200+ apps from 150 creators)
- Unitree (G1 humanoid $16,000+ base; H2 starts $29,900 commercial / $40,900 EDU; Go2 quadruped ~$2,800)
- PartaBot (assembled SO-ARM101, US-based)
- Waveshare (SO-ARM kits with resin frames)