Navigation method moves large obstacles to clear robot paths
Manipulation Feasible Navigation Among Movable Obstacles with Discrete Contact Pushing
Robotics
Summary
Robots often struggle to find efficient ways around big objects that block their path. The authors developed a system that helps robots not just avoid, but also move obstacles by pushing them carefully to new spots. They combine smart planning with a computer model that helps figure out when and how to push boxes. The robot learns how to push in different ways so it can clear a path and keep moving. The system works in both computer tests and real robot experiments.
What this means in practice
- •For warehouse automation teams: Enable robots to push large boxes aside to create efficient paths in cluttered storage areas.
- •For search and rescue crews: Provide mobile robots with the ability to move debris and obstacles to navigate blocked environments.
Authors
Shaohu Wang, Aiguo Song, Yulong Yuan, Zhongyu Sun, Tianyuan Miao, Qinjie Ji
Abstract
In environments with large movable obstacles, detour-only navigation can be inefficient or even infeasible, while obstacle interaction requires reasoning about navigation benefit, feasible placement, and executable manipulation. We present a hierarchical navigation among movable obstacles (NAMO) framework for mobile manipulators. At the high level, the planner identifies key blocking obstacles from reference paths and searches for relocation plans that jointly satisfy geometric, manipulation, and downstream navigation constraints. When direct relocation is hindered by other movable objects, a large language model (LLM) is selectively invoked to infer auxiliary manipulation dependencies, which are then verified by deterministic geometric planning. To execute the resulting relocation goals, we define discrete contact modes on the surfaces of box-shaped obstacles and select contact faces and regions online based on position and orientation errors, enabling straight, side, and corner pushing through contact switching. A recurrent reinforcement-learning policy coordinates the mobile base and manipulator to track tool center point (TCP) targets while preserving end-effector reachability during sustained pushing. Simulation and real-robot experiments demonstrate feasible navigation-manipulation in detour, single- and multi-obstacle relocation, and dependency-constrained scenarios, validating the framework for interactive navigation with large non-graspable obstacles. The open-source project is available at https://cloudytosunny.github.io/NAMO_DCPushing/.