CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation

TL;DR

CARE is a modular safety enhancement for visual navigation that uses repulsive forces from depth estimation to prevent collisions, improving robustness without retraining or additional sensors.

Contribution

The paper introduces CARE, a novel attachable module that enhances safety in visual navigation by dynamically adjusting trajectories using depth-based repulsive forces, compatible with existing models.

Findings

Significantly reduces collision rates in real-world tests.

Increases collision-free travel distance up to 10.7 times.

Maintains navigation performance while improving safety.

Abstract

We propose CARE (Collision Avoidance via Repulsive Estimation) to improve the robustness of learning-based visual navigation methods. Recently, visual navigation models, particularly foundation models, have demonstrated promising performance by generating viable trajectories using only RGB images. However, these policies can generalize poorly to environments containing out-of-distribution (OOD) scenes characterized by unseen objects or different camera setups (e.g., variations in field of view, camera pose, or focal length). Without fine-tuning, such models could produce trajectories that lead to collisions, necessitating substantial efforts in data collection and additional training. To address this limitation, we introduce CARE, an attachable module that enhances the safety of visual navigation without requiring additional range sensors or fine-tuning of pretrained models. CARE can be integrated seamlessly into any RGB-based navigation model that generates local robot trajectories. It dynamically adjusts trajectories produced by a pretrained model using repulsive force vectors computed from depth images estimated directly from RGB inputs. We evaluate CARE by integrating it with state-of-the-art visual navigation models across diverse robot platforms. Real-world experiments show that CARE significantly reduces collisions (up to 100%) without compromising navigation performance in goal-conditioned navigation, and further improves collision-free travel distance (up to 10.7x) in exploration tasks. Project page: https://airlab-sogang.github.io/CARE/