Event
Introducing SidewalkBench, a benchmark for urban sidewalk visual navigation
1 reports · 1 sources
Zhizheng Liu et al. propose SidewalkBench, an evaluation benchmark for urban sidewalk visual navigation built on NVIDIA Isaac Sim. It provides GPU-accelerated, high-fidelity sidewalk environments, including procedurally generated and real-scanned scenes, and incorporates event-driven pedestrian reaction behaviors. The authors evaluated 9 visual navigation models on 330 unit-test scenarios, 800 pedestrian-reaction scenarios, and 105 long-horizon scenarios. Their conclusion is that pedestrian interaction and long-horizon robustness remain key bottlenecks for existing models, and that scaling up sidewalk synthetic data for training is a viable direction.
Report timeline
- SidewalkBench: A benchmark for visual navigation on urban sidewalks
SidewalkBench is a benchmark for visual navigation on urban sidewalks built on NVIDIA Isaac Sim. It provides GPU-accelerated, high-fidelity sidewalk environments, including procedurally generated and real-world scanned scenes, and adds event-driven pedestrian reactive behaviors. The authors evaluated 9 visual navigation models on 330 unit-test scenarios, 800 pedestrian-reactive scenarios, and 105 long-horizon scenarios. They found that pedestrian interaction and long-horizon robustness remain key bottlenecks for existing models, and that scaling up sidewalk training with synthetic data is a viable direction.
arXiv cs.RO ·