Reactive Exploration of Unknown Environments for Redundant Robots using Virtual Model Control

2026-10-06

AI Summary

This study addresses the challenge of simultaneously satisfying geometric constraints and dynamic obstacle avoidance during exploration of constrained, occluded spaces by redundant robots. We propose an active exploration method based on Virtual Model Control (VMC). The core innovation lies in a novel voxel-level direct scoring mechanism that integrates current state information with information gain. Coupled with an eye-in-hand camera configuration, this approach enables whole-body reactive obstacle avoidance and efficient information acquisition without requiring path replanning. Both simulation and real-world experiments demonstrate that the proposed method achieves over 90% map coverage within 120 seconds while maintaining zero collisions throughout the exploration process, thereby validating its safety and efficiency in complex environments.

Abstract

The exploration of confined, occluded, and partially known spaces poses significant challenges in robotic manipulation. The overall pose of the robotic arm must be carefully controlled to respect tight geometric constraints while avoiding newly discovered obstacles. We address this problem by proposing an active exploration approach for redundant robotic arms with an eye-in-hand camera configuration. Our approach navigates and acquires information in real-time based on a novel scoring method that directly selects a target voxel from the unexplored space using the robot's current state and expected information gain. To move the robot safely toward the target voxel, we utilize Virtual Model Control, which guarantees compliance and enables whole-body reactive obstacle avoidance without the need for path replanning. Simulated and real-robot experiments in both confined and open environments demonstrate the effectiveness of our approach, achieving over $90\%$ mapping coverage across all tested environments in under $120$ seconds without colliding with obstacles.

Problem

• Reactive Exploration
• Unknown Environments
• Redundant Robots
• Robotic Manipulation
• Obstacle Avoidance

Innovation

• Reactive Exploration
• Redundant Robots
• Virtual Model Control
• Information Gain
• Obstacle Avoidance