# CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation Source: [CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:22:00.744Z Authors: Joonkyung Kim, Joonyeol Sim, Woojun Kim, Katia Sycara, Changjoo Nam Published: 2025-06-04T11:02:15.000Z ## 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/ ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Navigation on TurtleBot4 Environment TE](): Navigation; TurtleBot4 Environment TE; Goal Arrival Rate: 40. - [Visual Navigation on Dynamic-obstacle scenario Corner-appear](): Visual Navigation; Dynamic-obstacle scenario Corner-appear; Collisions Count (Corner-appear): 2. - [Visual Navigation on Dynamic-obstacle scenario Front-approach](): Visual Navigation; Dynamic-obstacle scenario Front-approach; Collision Rate: 0.2. - [Navigation on RoboMaster Environment TE](): Navigation; RoboMaster Environment TE; Goal Arrival Rate: 50. - [Navigation on TurtleBot4 Environment CY](): Navigation; TurtleBot4 Environment CY; Goal Arrival Rate: 30. - [Navigation on RoboMaster Environment CY](): Navigation; RoboMaster Environment CY; Goal Arrival Rate: 10. - [Navigation on LoCoBot Environment TE](): Navigation; LoCoBot Environment TE; Goal Arrival Rate: 0. - [Navigation on LoCoBot Environment CY](): Navigation; LoCoBot Environment CY; Goal Arrival Rate: 40. ## Original sources and implementation [Original paper]() [PDF]()