Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors

Agentic AI
Published: arXiv: 2508.13151v1
Authors

Yuying Zhang Joni Pajarinen

Abstract

Mobile manipulation in dynamic environments is challenging due to movable obstacles blocking the robot's path. Traditional methods, which treat navigation and manipulation as separate tasks, often fail in such 'manipulate-to-navigate' scenarios, as obstacles must be removed before navigation. In these cases, active interaction with the environment is required to clear obstacles while ensuring sufficient space for movement. To address the manipulate-to-navigate problem, we propose a reinforcement learning-based approach for learning manipulation actions that facilitate subsequent navigation. Our method combines manipulability priors to focus the robot on high manipulability body positions with affordance maps for selecting high-quality manipulation actions. By focusing on feasible and meaningful actions, our approach reduces unnecessary exploration and allows the robot to learn manipulation strategies more effectively. We present two new manipulate-to-navigate simulation tasks called Reach and Door with the Boston Dynamics Spot robot. The first task tests whether the robot can select a good hand position in the target area such that the robot base can move effectively forward while keeping the end effector position fixed. The second task requires the robot to move a door aside in order to clear the navigation path. Both of these tasks need first manipulation and then navigating the base forward. Results show that our method allows a robot to effectively interact with and traverse dynamic environments. Finally, we transfer the learned policy to a real Boston Dynamics Spot robot, which successfully performs the Reach task.

Paper Summary

Problem
The main problem this paper addresses is how to enable robots to effectively navigate dynamic environments where obstacles can move or return to their original positions. This "manipulate-to-navigate" challenge requires the robot to interact with its environment by moving objects out of the way before it can safely move forward.
Key Innovation
What's new and unique about this work is a reinforcement learning-based approach that integrates manipulability priors (which help focus the robot on high-manipulability body positions) and visual affordance maps (which select high-quality manipulation actions). This combination reduces unnecessary exploration and allows the robot to learn manipulation strategies more effectively.
Practical Impact
This research has significant practical implications. By enabling robots to successfully navigate dynamic environments, this work has applications in areas such as human assistance, manufacturing, and agriculture, where mobile manipulators can perform complex tasks that involve both navigation and manipulation. The proposed approach could also be used in search and rescue scenarios or other situations where the environment is unpredictable.
Analogy / Intuitive Explanation
Think of a robot trying to navigate through a crowded room. To get to its destination, it needs to move obstacles (like people) out of the way first. This paper proposes a way for the robot to learn how to effectively "manipulate" these obstacles using visual cues and prior knowledge about what actions are likely to be successful. By doing so, the robot can reduce the complexity of the task and focus on finding the best path forward. Let me know if you'd like me to make any changes!
Paper Information
Categories:
cs.RO cs.SY eess.SY
Published Date:

arXiv ID:

2508.13151v1

Quick Actions