Search papers, labs, and topics across Lattice.
This study introduces a data-efficient method for dynamic obstacle avoidance in autonomous robots operating in unstructured environments, utilizing a pretrained monocular depth estimation model called UniDepth to generate dense depth maps from RGB video. By extending the SuperPoint and SuperGlue feature correspondence pipeline, the method tracks keypoints across frames and computes time-to-collision (TTC) to inform evasive maneuvers. The approach achieves notable performance, detecting critical TTC frames in 20 out of 22 unique obstacles, while requiring minimal training data compared to traditional end-to-end learned methods.
Achieving 84% accuracy in evasive motion direction while needing only 74 seconds of data for hyperparameter tuning, this method redefines data efficiency in obstacle avoidance for robots.
Dynamic obstacle avoidance in unstructured outdoor environments remains a critical challenge for autonomous mobile robots, particularly when large-scale robot-specific training data and simulation-based policies are impractical. We present a data-efficient, interpretable method for vision-based dynamic obstacle avoidance that operates entirely on real-world data, avoiding the sim-to-real transfer problem inherent in simulation-trained policies. Our approach leverages UniDepth, a large pretrained monocular depth estimation model, to produce dense depth maps from RGB video without requiring stereo cameras or LiDAR at inference time. Dynamic obstacle avoidance is achieved by extending the SuperPoint and SuperGlue feature correspondence pipeline to track keypoints across long frame sequences, projecting their 2D pixel-space positions into 3D using camera intrinsics and predicted depth, running bundle adjustment initialized from these 3D keypoints, and computing per-keypoint time-to-collision (TTC). A 2D motion primitive in the ground plane is then selected to move the robot away from the closest point of approach of the minimum-TTC keypoint. Evaluated on real-world data from the M3ED dataset, our pipeline achieves a precision of 0.49 and a recall of 0.38 in identifying frames with a ground truth TTC below 1 second, and correctly generates the evasive motion direction in 84\% of true positive detections. Crucially, it detects at least one frame with TTC less than 1 second for 20 out of 22 unique physical obstacles present in our test sequences. Unlike end-to-end learned methods that demand thousands of hours of robot-specific training data, our approach eliminates model training entirely, requiring only 74 seconds of data for hyperparameter tuning. This demonstrates exceptional data efficiency while preserving interpretable and generalizable behavior across diverse obstacle types.
