Search papers, labs, and topics across Lattice.
5
0
4
7
Transforming kinematically feasible motion references into dynamically accurate trajectories could revolutionize how robots learn complex contact-rich behaviors.
A humanoid robot can dodge 95% of thrown balls using only depth data from a head-mounted camera, showcasing the potential of perception-aware safety in dynamic environments.
MPC-RL achieves superior humanoid locomotion and manipulation performance by integrating efficient MPC guidance, challenging the traditional RL training paradigms.
HANDOFF redefines humanoid robot control by seamlessly integrating diverse manipulation skills into a single, intuitive command interface.
Domain randomization doesn't just make your robot policies more robust; it fundamentally warps the optimization landscape, potentially guiding your search towards better contact-rich behaviors.
