DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic Manipulation

TL;DR

This paper introduces DORA, a reinforcement learning framework that uses object affordance maps to improve dexterous robotic manipulation, achieving higher success rates and better semantic alignment in complex tasks.

Contribution

We propose a novel affordance-guided RL approach that incorporates semantic object understanding into manipulation policy learning for robotic hands.

Findings

Improves task success rates by 15.4% on average.

Enhances sample efficiency and policy generalization.

Demonstrates effectiveness across multiple manipulation tasks.

Abstract

Dexterous robotic manipulation remains a longstanding challenge in robotics due to the high dimensionality of control spaces and the semantic complexity of object interaction. In this paper, we propose an object affordance-guided reinforcement learning framework that enables a multi-fingered robotic hand to learn human-like manipulation strategies more efficiently. By leveraging object affordance maps, our approach generates semantically meaningful grasp pose candidates that serve as both policy constraints and priors during training. We introduce a voting-based grasp classification mechanism to ensure functional alignment between grasp configurations and object affordance regions. Furthermore, we incorporate these constraints into a generalizable RL pipeline and design a reward function that unifies affordance-awareness with task-specific objectives. Experimental results across three manipulation tasks - cube grasping, jug grasping and lifting, and hammer use - demonstrate that our affordance-guided approach improves task success rates by an average of 15.4% compared to baselines. These findings highlight the critical role of object affordance priors in enhancing sample efficiency and learning generalizable, semantically grounded manipulation policies. For more details, please visit our project website https://sites.google.com/view/dora-manip.