RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
RoboSPA introduces a 527K-trajectory benchmark with 280 task variants showing current VLA models struggle with spatial reasoning and long-horizon planning.
RoboSPA is a large-scale robotic manipulation dataset and benchmark for diagnosing embodied reasoning in vision-language-action models, covering fine-grained spatial reasoning and long-horizon procedural planning. It spans 10 task categories and 56 base tasks instantiated across five difficulty levels for 280 variants, with 527K trajectories collected across multiple embodiments and diverse scenes. Diagnostic metrics go beyond binary success rates, and experiments show current VLA models struggle with complex spatial relations, precise low-level execution, and memory-intensive planning.
- 280 task variants across 56 base tasks with five difficulty levels.
- 527K trajectories collected across multiple embodiments and diverse scenes.
- Introduces diagnostic metrics beyond binary task success rate.
- Current VLA models fail at complex spatial relations and memory-heavy planning.
- AI models
- RoboSPA
From the original article
1 min read at huggingface.co
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task completion under predefined settings, offering limited insight into model reasoning under increasing spatial and procedural complexity.
By Zhenxuan Fan, Bo Zhang, Yutong Lin · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.