Slug Mobile: Test-Bench for RL Testing
This addresses the problem of model transferability from simulation to reality for autonomous vehicles, though it appears incremental as it builds on existing small-scale AV platforms with an added sensor.
The paper tackles the sim-to-real gap in reinforcement learning for autonomous vehicles by introducing Slug Mobile, a one-tenth scale vehicle test-bench that includes a Dynamic Vision Sensor to enable training of Spiking Neural Networks on neuromorphic hardware.
Sim-to real gap in Reinforcement Learning is when a model trained in a simulator does not translate to the real world. This is a problem for Autonomous Vehicles (AVs) as vehicle dynamics can vary from simulation to reality, and also from vehicle to vehicle. Slug Mobile is a one tenth scale autonomous vehicle created to help address the sim-to-real gap for AVs by acting as a test-bench to develop models that can easily scale from one vehicle to another. In addition to traditional sensors found in other one tenth scale AVs, we have also included a Dynamic Vision Sensor so we can train Spiking Neural Networks running on neuromorphic hardware.