Lab 07

Intelligent Machines Lab

The brain for the next robot.

The control intelligence for new-age robotics — built, not trained. We use Reverse Synthetic Neural Networks to compile a model for each robotic capability directly from human motion, with no GPU training: a library of drop-in skills — grasp and hand articulation, bipedal gait and balance, gaze and facial/mouth actuation — that run on the robot itself, in real time, at the edge. A small team can own a capability end-to-end, and each capability is independently and commercially valuable.

§ 01

Open problems

Where a well-posed attempt could move the frontier.

  • 01Pre-synthesized RSN neuron libraries that compile a control model for each robotic capability — hand/grasp articulation, bipedal gait and balance, gaze and mouth/facial actuation — directly from human motion capture, without gradient training
  • 02Closed-form motor-primitive synthesis: human-like movement learned from a handful of demonstrations, with no reinforcement-learning rollouts
  • 03Real-time, on-device inference for actuator control on low-power robot hardware — no datacentre in the loop
  • 04A portable capability marketplace: drop-in skill models (walk, grasp, speak) that transfer across robot chassis