Search papers, labs, and topics across Lattice.
This paper introduces Contact Coverage-Guided Exploration (CCGE), a novel exploration method for general-purpose dexterous manipulation that addresses the lack of well-defined reward structures in this domain. CCGE represents contact state as the intersection between object surface points and predefined hand keypoints, maintaining a contact counter conditioned on discretized object states to capture finger-object interaction frequency. By using this counter to assign both a count-based contact coverage reward and an energy-based reaching reward, CCGE significantly improves training efficiency and success rates across a diverse set of dexterous manipulation tasks, demonstrating robust transfer to real-world robotic systems.
Forget hand-crafted rewards: this new method learns dexterous manipulation by encouraging the robot hand to explore diverse contact patterns on objects, leading to impressive real-world transfer.
Deep Reinforcement learning (DRL) has achieved remarkable success in domains with well-defined reward structures, such as Atari games and locomotion. In contrast, dexterous manipulation lacks general-purpose reward formulations and typically depends on task-specific, handcrafted priors to guide hand-object interactions. We propose Contact Coverage-Guided Exploration (CCGE), a general exploration method designed for general-purpose dexterous manipulation tasks. CCGE represents contact state as the intersection between object surface points and predefined hand keypoints, encouraging dexterous hands to discover diverse and novel contact patterns, namely which fingers contact which object regions. It maintains a contact counter conditioned on discretized object states obtained via learned hash codes, capturing how frequently each finger interacts with different object regions. This counter is leveraged in two complementary ways: (1) to assign a count-based contact coverage reward that promotes exploration of novel contact patterns, and (2) an energy-based reaching reward that guides the agent toward under-explored contact regions. We evaluate CCGE on a diverse set of dexterous manipulation tasks, including cluttered object singulation, constrained object retrieval, in-hand reorientation, and bimanual manipulation. Experimental results show that CCGE substantially improves training efficiency and success rates over existing exploration methods, and that the contact patterns learned with CCGE transfer robustly to real-world robotic systems. Project page is https://contact-coverage-guided-exploration.github.io.
