SafeBench

SafeBench is a benchmarking platform designed for the safety evaluation of autonomous vehicles (AVs) in safety-critical scenarios¹. It aims to provide a unified platform that integrates various types of safety-critical testing scenarios, scenario generation algorithms, and other variations such as driving routes and environments¹. The platform implements four deep reinforcement learning-based AV algorithms with four types of input to perform fair comparisons on SafeBench¹.

The creators of SafeBench have observed that machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts, especially in safety-critical domains like autonomous driving¹. Traditional AD testing requires extensive driving miles due to the high dimensionality and rarity of safety-critical scenarios in the real world. SafeBench addresses this challenge by providing a large-scale and effective testing environment that encourages the development of new testing scenario generation and safe AD algorithms¹.

(1) SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous .... https://arxiv.org/abs/2206.09682. (2) GitHub - trust-ai/SafeBench: A Benchmark for Evaluating Autonomous .... https://github.com/trust-ai/SafeBench. (3) SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous .... https://arxiv.org/pdf/2206.09682v1. (4) undefined. https://doi.org/10.48550/arXiv.2206.09682. (5) undefined. https://bing.com/search?q=.