Driving · 2026-10-16
From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion
Bazeela Banday, Jishnu Keshavan
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors present a monocular visual safety-certification approach that uses scale-free, depth-normalized relative motion from optical flow to certify collision risk. A Concurrent Learning observer estimates the depth-normalized relative velocity with a computable estimation-error bound, which is propagated into a Robust Vision-Based Collision Cone Control Barrier Function (RV-C3BF). An optimal-decay CBF-QP minimally filters a nominal command to enforce robust safety, validated on a TurtleBot3 with only monocular vision and proprioception.
Why it matters
The paper targets formal safety certification for monocular navigation without reconstructing metric obstacle position, velocity, geometry, or a metric world model. By turning depth-normalized relative-motion direction (from optical flow) into collision-cone constraints and explicitly accounting for estimation uncertainty and robot footprint, the authors aim to enable robust collision avoidance using only monocular sensing.
Method
- Use monocular optical flow with rotational compensation to obtain scale-free, depth-normalized relative motion for collision-cone construction, without reconstructing obstacle position/velocity/geometry or a metric world model.
- Train nothing: an online Concurrent Learning observer estimates the normalized relative velocity and provides a computable estimation-error bound under finite-time excitation and bounded-variation assumptions.
- Propagate the estimation-error bound into collision-cone angular inflation plus a monocular robot-footprint margin, forming RV-C3BF enforced via an optimal-decay CBF-QP.
Limitation
The authors report that all seven hardware failures occurred when obstacles entered the camera field of view at very close range, preventing timely perception updates; no failures were observed once a collision-cone representation had been established.
Abstract (from arXiv)
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.
Related papers
- BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
- LynxScenes: A Large-Scale Real-World Benchmark for Outdoor Wheel-Legged Robot Perception, Navigation, Imagination and Reconstruction
- Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model
- Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
- PhysWAM: Physically Consistent World Action Model for Autonomous Driving
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-15 · Indexed by Pub-AI: 2026-10-16 UTC
From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion
Preprint posted: 2026-10-15 · Original record ↗
- arxiv
- 2610.21374
Explicit source versions (1)
- v2 · 2026-10-19
- Explicit source version detected · v2
Source date: 2026-10-19 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:id explicit version (official metadata)
- Preprint available
Source date: 2026-10-15 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
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.
