Technical Report: Sensor-Based Reactive Symbolic Planning in Partially Known Environments

TL;DR

This paper introduces a sensor-based reactive symbolic planning method for robots to assemble objects in complex, partially known environments, combining high-level planning with reactive obstacle avoidance, validated through proofs and simulations.

Contribution

It presents a novel hybrid planning approach that integrates symbolic high-level planning with reactive control for assembly tasks in uncertain environments.

Findings

Method guarantees convergence and obstacle avoidance.

Validated through formal proofs and numerical simulations.

Effective in nonconvex, cluttered environments with unknown obstacle properties.

Abstract

This paper considers the problem of completing assemblies of passive objects in nonconvex environments, cluttered with convex obstacles of unknown position, shape and size that satisfy a specific separation assumption. A differential drive robot equipped with a gripper and a LIDAR sensor, capable of perceiving its environment only locally, is used to position the passive objects in a desired configuration. The method combines the virtues of a deliberative planner generating high-level, symbolic commands, with the formal guarantees of convergence and obstacle avoidance of a reactive planner that requires little onboard computation and is used online. The validity of the proposed method is verified both with formal proofs and numerical simulations.