Bench2FreeAD: A Benchmark for Vision-based End-to-end Navigation in Unstructured Robotic Environments
This work addresses the problem of enabling logistics and service robots to navigate unstructured environments, but it is incremental as it builds on existing methods with new data.
The paper tackles the lack of vision-based end-to-end autonomous driving algorithms for unstructured robotic environments by introducing the FreeWorld Dataset and a benchmark, showing that fine-tuning with this dataset significantly enhances navigation performance in such scenarios.
Most current end-to-end (E2E) autonomous driving algorithms are built on standard vehicles in structured transportation scenarios, lacking exploration of robot navigation for unstructured scenarios such as auxiliary roads, campus roads, and indoor settings. This paper investigates E2E robot navigation in unstructured road environments. First, we introduce two data collection pipelines - one for real-world robot data and another for synthetic data generated using the Isaac Sim simulator, which together produce an unstructured robotics navigation dataset -- FreeWorld Dataset. Second, we fine-tuned an efficient E2E autonomous driving model -- VAD -- using our datasets to validate the performance and adaptability of E2E autonomous driving models in these environments. Results demonstrate that fine-tuning through our datasets significantly enhances the navigation potential of E2E autonomous driving models in unstructured robotic environments. Thus, this paper presents the first dataset targeting E2E robot navigation tasks in unstructured scenarios, and provides a benchmark based on vision-based E2E autonomous driving algorithms to facilitate the development of E2E navigation technology for logistics and service robots. The project is available on Github.