ANR Robot™

We are a small R&D lab working to advance the state of the art for autonomous robots in unstructured environments. A secondary goal is to explore just how far a small company, research group, or hobbyist can go building on open-source software and off-the-shelf hardware.

Robots

Trossen AI Stationary Robot
pi0.5 learns multi-prompt policy for sub-tasks, e.g. 'pick up pink cube ...', see details
Gemini Robotics ER-1.5 HL controller chooses next subtask to 'put all cubes in the bucket'
Trossen AI Stationary Robot
pi0.5 policy for high dexterity task. But does it 'see' the string? see details
Trossen AI Stationary Robot
ACT policy rollout for 20mm box transfer, see details
Trossen AI Stationary Robot
ACT policy rollout for popping lid, see details
Trossen AI Stationary Robot
ACT policy rollout for pouring box, see details
Trossen AI Stationary Robot
pi0 LoRA finetuned policy from SIMULATED dataset with red cube, see details
Trossen AI Stationary Robot
pi0 full finetuned policy from small multi-lid multi-pot dataset, see details
Trossen AI Stationary Robot
pi0 full finetuned policy from small multi-lid multi-pot dataset (close), see details

Hierarchical Planning

Recursive Tree Planner
Builds a stack of 5 blocks in Box2d
Recursive Tree Planner
Solves Lunar Lander in Box2d
(Problem from Gymnasium)
Recursive Tree Planner
Solves Inverted Pendulum in Mujoco
(Problem from Levy et al)
Recursive Tree Planner
Solves 3 Level Four Rooms
(Problem from Levy et al)
Paper: Pure Planning to Pure Policies and In Between with a Recursive Tree Planner