Monocular vision guides safe robot navigation amid obstacles
From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion
Robotics
Summary
Seeing obstacles clearly is hard for robots using just one camera because they can't measure distances directly. The authors created a way to judge how close and risky collisions are by looking at how things move relative to the robot, without figuring out exact sizes or positions. They built math tools to estimate and handle uncertainty in these measurements, helping the robot avoid crashes. Tests on a small robot showed it could navigate safely most of the time using only one camera and its own movement sensors.
What this means in practice
- •For robot developers: Enable robots using a single camera to safely navigate cluttered spaces without needing full 3D maps.
- •For drone operators: Provide drones with safer collision avoidance capabilities based on relative motion cues from monocular cameras.
Authors
Bazeela Banday, Jishnu Keshavan
Abstract
Safe autonomous navigation using monocular vision remains challenging because explicit obstacle states are not directly observable. This letter introduces a visual safety-certification paradigm that uses scale-free, depth-normalized relative motion encoded by monocular optical flow as the representation for collision-risk certification, without reconstructing obstacle position, velocity, geometry, or a metric world model. Unlike conventional optical-flow-based navigation approaches that rely on image motion to shape avoidance behavior, the proposed framework directly encodes collision-cone geometry and safety constraints in this relative-motion representation. An online Concurrent Learning observer estimates the normalized relative velocity and provides a computable estimation-error bound. This uncertainty is propagated into the collision cone through angular inflation and a monocular robot-footprint margin, yielding a Robust Vision-Based Collision Cone Control Barrier Function (RV-C$^3$BF). An optimal-decay CBF quadratic program minimally modifies the nominal control input to enforce the resulting robust safety constraint under the stated assumptions. Extensive simulation and real-world experiments on a TurtleBot3 in cluttered environments with static and dynamic obstacles demonstrate collision avoidance using only monocular vision and onboard proprioception, with the estimation-error bound containing the measured error in $98.3\%$ of simulation samples and the robot achieving collision-free navigation in $93$ of $100$ real-world trials.