PCG-based Static Underground Garage Scenario Generation
This addresses the need for efficient scenario generation in autonomous driving training, particularly for underground garages, but appears incremental as it applies an existing algorithm to a specific domain.
The paper tackles the problem of generating static underground garage scenarios for autonomous driving training by framing it as a procedural content generation (PCG) problem and using the Sarsa algorithm to solve it, aiming to reduce manual effort and resource consumption compared to real-world data or manually constructed simulations.
Autonomous driving technology has five levels, from L0 to L5. Currently, only the L2 level (partial automation) can be achieved, and there is a long way to go before reaching the final level of L5 (full automation). The key to crossing these levels lies in training the autonomous driving model. However, relying solely on real-world road data to train the model is far from enough and consumes a great deal of resources. Although there are already examples of training autonomous driving models through simulators that simulate real-world scenarios, these scenarios require complete manual construction. Directly converting 3D scenes from road network formats will lack a large amount of detail and cannot be used as training sets. Underground parking garage static scenario simulation is regarded as a procedural content generation (PCG) problem. This paper will use the Sarsa algorithm to solve procedural content generation on underground garage structures.