Ahmed Doghri Logo Image
Ahmed Doghri

safepathshield

The nominal path spends 39 steps in collision. Seventy-five minimal interventions keep every shielded step safe and still reach the goal.

safepathshield robot path safety field
safepathshield working browser demo

A Learned Policy Is Not A Safety Case

A goal-seeking policy can be effective on average and still issue one command that crosses an obstacle boundary.

safepathshield wraps nominal velocity with an analytical control-barrier projection: unchanged when safe, minimally corrected when the barrier inequality would be violated.

The Demo

The nominal controller records 39 collision steps. The shield intervenes 75 times, preserves 0.00137 positive minimum clearance, records zero collisions, and reaches the goal with 0.05978 error.

The fixture is a deterministic single-integrator robot with one circular obstacle. Physical deployment requires full dynamics, uncertainty, actuator limits, state estimation, and hardware validation.

Research Basis

Current work combines learned control-barrier functions with formal verification and reinforcement-learning safety layers.

Read the Control-barrier verification at PMLR 2025.

Tools Used

Python
Robotics
Control Barrier Functions
Safe RL
Simulation
Docker
GitHub Actions CI