Correcting Autonomous Vehicle Behavior to Ensure Rule Compliance
Felipe Toledo, Trey Woodlief, Sebastian Elbaum, Matthew Dwyer
AI summary
Problem
Existing AV compliance methods require access to system internals or rely on narrow architectural assumptions, limiting their generality and preventing runtime guarantees for diverse deployed systems.
Approach
M4PC maps raw sensor data to driving rules via scene graph abstractions, then minimally adjusts the vehicle's control outputs to keep them within a mathematically defined safe region that satisfies all active safety postconditions.
Key results
- Validated across three diverse AV architectures in the CARLA simulator
- Outperforms baselines and matches training-optimized systems with accurate scene graphs
- Achieves comparable compliance to training-optimized baselines with current scene graph implementation
- Enables runtime correction for heterogeneous, non-differentiable systems without internal access
Why it matters
Offers a deployable, architecture-independent safety layer for autonomous vehicles, addressing a critical gap in real-world rule compliance and system generalization.
Abstract
As autonomous vehicles (AVs) continue to gain promi- nence in public life, the cost of their failures becomes increasingly drastic, endangering human life. Such failures arise from AVs’ inability to meet their safety specifications in the field. Recent works have aimed to improve AVs’ compliance with their safety specification through improved training and runtime enforcement. However, these methods are limited, requiring access to system internals or relying on narrow assumptions, which reduces their generality. In this work, we propose a different paradigm, Monitoring for Property Compliance (M4PC), which independently evaluates the system’s compliance with the specification. The approach operates in two steps. First, it leverages scene graph abstractions and a specialized graph generator to map sensor data to driving rule preconditions to determine if an intervention is needed. Second, to correct an erroneous system output, M4PC defines a safe region within the control space defined by all relevant postconditions and minimally alters the system’s output to ensure it remains within this safe region, thereby preventing property violations. We apply M4PC to improve the specification compliance of three state-of-the-art autonomous vehicles with varying architec- tures in the CARLA simulator. Our current implementation can improve a baseline system, while our most optimized implementation outperforms state-of-the-art techniques that require system access.