Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid

2025-05-06

AI Summary

Ensuring safe, autonomous collision avoidance for high-speed aerial vehicles in dense, shared airspace remains a critical challenge—particularly for resource-constrained platforms requiring real-time, verifiably safe separation. Method: This work proposes an end-to-end vision-driven airborne collision avoidance system. It innovatively encodes Control Barrier Functions (CBFs) directly into the perception input space, establishing the first perception-driven safety threshold. The system integrates a learning-based edge AI framework with SWaP-C-optimized multi-camera hardware and employs joint validation via digital twin simulation and real-world flight testing. Contribution/Results: It achieves the world’s first real-world, purely vision-based high-speed collision avoidance demonstration at a 144 km/h closing speed. The system attains 100% autonomous separation success across diverse aircraft types, complex geometric configurations, and challenging environmental conditions—including adverse weather and variable illumination—thereby establishing a new benchmark for vision-only high-speed collision avoidance.

Technology Category

• Computer Vision: Vision for Robotics & Autonomous Driving
• Application Domains: Mobility, Driving & Flight
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Data transparency and provenance

Abstract

Assured safe-separation is essential for achieving seamless high-density operation of airborne vehicles in a shared airspace. To equip resource-constrained aerial systems with this safety-critical capability, we present ViSafe, a high-speed vision-only airborne collision avoidance system. ViSafe offers a full-stack solution to the Detect and Avoid (DAA) problem by tightly integrating a learning-based edge-AI framework with a custom multi-camera hardware prototype designed under SWaP-C constraints. By leveraging perceptual input-focused control barrier functions (CBF) to design, encode, and enforce safety thresholds, ViSafe can provide provably safe runtime guarantees for self-separation in high-speed aerial operations. We evaluate ViSafe's performance through an extensive test campaign involving both simulated digital twins and real-world flight scenarios. By independently varying agent types, closure rates, interaction geometries, and environmental conditions (e.g., weather and lighting), we demonstrate that ViSafe consistently ensures self-separation across diverse scenarios. In first-of-its-kind real-world high-speed collision avoidance tests with closure rates reaching 144 km/h, ViSafe sets a new benchmark for vision-only autonomous collision avoidance, establishing a new standard for safety in high-speed aerial navigation.

Problem

• Ensuring safe-separation for high-density airborne vehicles
• Developing vision-only collision avoidance for resource-constrained systems
• Providing runtime safety guarantees in high-speed aerial operations

Innovation

• Vision-only airborne collision avoidance system
• Learning-based edge-AI framework integration
• Perceptual input-focused control barrier functions