Wirewalk Instituteof AI
hw-207 Intermediate Waitlist

Robotics and Physical AI Hardware

For engineers and technical buyers who need to specify the compute, sensors, actuators, power and safety hardware for robots that run AI models, from mobile manipulators to humanoids.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

Physical AI moves models off the data-center floor and into machines that see, move and touch. The hardware choices decide what the AI can do: a policy cannot outperform its cameras, its actuators' torque and backdrivability, its compute's latency, or its battery. This course gives engineers a working map of that hardware, organized around the questions a robot program has to answer.

You start with robot architectures, from arms and mobile manipulators to legged and humanoid platforms, and how degrees of freedom, payload and reach translate into a hardware bill of materials. You then compare onboard compute (NVIDIA Jetson AGX Thor and Orin, Qualcomm Dragonwing robotics processors, and offload to edge servers), focusing on what perception and vision-language-action workloads need rather than restating the Jetson internals covered in hw-206. The sensing module covers RGB, stereo and time-of-flight depth, LiDAR, IMUs, force-torque and tactile sensors, and synchronization; the actuation module covers motors, harmonic and planetary gearing, quasi-direct-drive and series-elastic actuators, and end effectors. The last modules cover real-time communication (EtherCAT, CAN FD, Time-Sensitive Networking, ROS 2 middleware), battery and thermal design, and functional safety under the 2025 editions of ISO 10218 and related standards. Product facts are current as of October 2026.

What you will be able to do

  • Translate a robot task into requirements for degrees of freedom, payload, reach, speed and runtime
  • Select onboard compute for perception and VLA workloads and decide what to offload to the edge or cloud
  • Choose and place cameras, depth sensors, LiDAR, IMUs and tactile sensors and plan their time synchronization
  • Compare actuator and gearbox types for torque density, backdrivability and safe human contact
  • Design a real-time control and data network using EtherCAT, CAN FD or TSN alongside ROS 2
  • Size batteries, power distribution and thermal management for a mobile robot
  • Identify the functional-safety standards and safety functions that apply to a given robot application

Syllabus

6 modules · 21 lessons · about 12 hours

Module 1: Robot architectures and requirements

From task to platform: how form factor drives every hardware choice.
3 lessons
  1. Arms, mobile manipulators, legged robots and humanoids: what each form factor is for
  2. From task to spec: degrees of freedom, payload, reach, speed and duty cycle
  3. The physical-AI bill of materials and where the cost and weight go

Module 2: Onboard and offboard compute

Running perception and foundation-model policies within power and latency limits.
4 lessons
  1. Workload profiles: perception, SLAM, motion planning and VLA inference
  2. Jetson AGX Thor and Orin for robots: power modes, multi-camera I/O and functional-safety islands
  3. Alternative robot compute: Qualcomm Dragonwing, x86 industrial PCs and safety MCUs
  4. Splitting work across robot, edge server and cloud: latency, connectivity and failure modes

Module 3: Sensing the world

The sensors that feed robot perception and policies.
4 lessons
  1. Cameras for robots: global versus rolling shutter, GMSL and MIPI, HDR and calibration
  2. Depth and range: stereo, time-of-flight, structured light and LiDAR
  3. Proprioception and touch: encoders, IMUs, force-torque and tactile sensors
  4. Time synchronization and sensor fusion: PTP, hardware triggering and timestamps

Module 4: Actuation and manipulation

Motors, transmissions and hands, and how they shape what a policy can learn.
3 lessons
  1. Motors and drives: BLDC, frameless torque motors and field-oriented control
  2. Gearing and actuator designs: harmonic, planetary and cycloidal, quasi-direct-drive and series-elastic
  3. Grippers and dexterous hands: parallel-jaw, suction and multi-finger designs

Module 5: Communication, power and thermals

The real-time buses, batteries and cooling that keep a robot running.
4 lessons
  1. Real-time buses: EtherCAT, CAN FD and Time-Sensitive Networking
  2. ROS 2 on real hardware: DDS middleware, ros2_control and real-time kernels
  3. Batteries and power distribution: chemistries, runtime sizing, BMS and hot-swap
  4. Thermal design for sealed and mobile robots

Module 6: Safety, standards and platform selection

Making robots safe around people and choosing a platform with confidence.
3 lessons
  1. Functional safety basics: ISO 13849, IEC 61508 and safety functions such as safe torque off
  2. Robot-specific standards: ISO 10218:2025, collaborative applications and mobile and service robots
  3. Evaluating a robot platform: openness, SDKs, serviceability and total cost

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by NVIDIA (Jetson AGX Thor, Jetson Orin, Holoscan Sensor Bridge), Qualcomm (Dragonwing robotics processors), ROS 2, EtherCAT Technology Group, Unitree, Universal Robots, Franka Robotics, RealSense, Ouster, or Hesai. Product and company names are trademarks of their respective owners.

hw-001 Free intro Available

Inside an AI Data Center: GPUs, Networks and Storage in One Hour

A plain-English, one-hour walk through an AI data center: what a model asks of hardware, what is inside a GPU server, how GPUs talk over NVLink, InfiniBand and Ethernet, where the data lives, and why AI racks need so much power and cooling.

1 h · 6 lessons Free intro
hw-101 Basic Available

AI Hardware Fundamentals: GPUs, CPUs, Memory, Networking and Storage

A plain-language tour of the hardware that runs AI: why AI is limited by compute, memory bandwidth and data movement; what GPUs, HBM and precision formats are; how servers, networks, storage, power and cooling fit together; and how to size a simple inference or training system and weigh cloud against buying.

8 h · 20 lessons See price at checkout
hw-201 Intermediate Available

GPU Hardware Deep Dive: Architecture, Memory and Interconnects

An engineer's tour of the modern data center GPU: how SMs and CUs, warps and wavefronts, tensor and matrix cores and the on-chip memory hierarchy work; what FP64 through FP4 and sparsity really buy you; how HBM, PCIe, NVLink, Infinity Fabric, UALink and CXL move data; and how power, cooling and reliability features shape real deployments. Reviewed against vendor sources as of October 2026.

14 h · 21 lessons See price at checkout