PRESTO: Fast motion planning using diffusion models based on key-configuration environment representation.

Prime the Search: Using Large Language Models for Guiding Geometric Task and Motion Planning by Warm-starting Tree Search.

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks

Open X-Embodiment: robotic learning datasets and RT-X models

Learning whole-body manipulation for quadrupedal robot

Preference learning for guiding the tree search in continuous POMDPs

Pre- and Post-Contact Policy Decomposition for Non-Prehensile Manipulation with Sim-to-Real Transfer.

Local object crop collision network for efficient simulation of non-convex objects in GPU-based simulators.

Ohm^2: Optimal hierarchical planner for object search in large environments via mobile manipulation