RoboBugBench: Benchmarking Automated Repair of Real Robot Software Under an Audited Behavioral Oracle
RoboBugBench is presented, a benchmark of 33 real, execution-validated defects in a pinned ROS 2 navigation stack, in which a candidate patch is graded by compiling it and driving the robot through a physics simulation rather than by running a unit test.
Alexey Tuzikov
· 0 citations