Search papers, labs, and topics across Lattice.
4
0
6
13
Achieving 100% success on complex robotic tasks with just one demonstration could revolutionize how we approach real-world robotic learning.
Continuous and consistent robotic actions can be achieved without additional network parameters, revolutionizing how robots interpret and execute complex tasks.
Skip the manual effort: CABTO uses large models to automatically generate complete and consistent behavior tree systems for robot manipulation.
Ditch the human supervisors: a multimodal agent can guide robotic reinforcement learning with corrective waypoints and spatial constraints, boosting sample efficiency beyond human-in-the-loop methods.
