cs.RONov 11, 2026

GraSLA: A Lightweight Spatial-Language-Action Model with Grasp Hypotheses as Geometric Priors

Authors: Jibao Yuan, Zixiang Zhao, Wensong Xu, Siqi Lu, Shaofei Chen

Organizations: College of Intelligence Science and Technology, National University of Defense Technology

Abstract

This paper focuses on improving the behavioral diversity and effectiveness of language-conditioned manipulation policies trained through imitation learning. Recently, continuous-action policies have become mainstream in robotic manipulation, but the lack of diverse demonstrations tends to restrict their behavioral diversity. For grasping, a fundamental subtask of manipulation, 6-DoF grasp detection provides diverse grasp hypotheses, but open-loop execution constrains responsiveness in dynamic environments. This motivates us to combine the diversity of grasp hypotheses with the adaptability of continuous-action policies. To this end, we propose GraSLA, a lightweight and effective spatial-language-action model with grasp hypotheses as geometric priors. In particular, we employ spatial and language foundation models to encode scene geometry and task semantics, and integrate them with grasp hypotheses through bidirectional cross-attention for continuous action prediction. On LIBERO, GraSLA achieves an average success rate of 99.30%.

Figures & tables

Explore similar work

CardsList
  1. SLA: Scaling Spatial-Language-Action Model via Continual Pre-training

    Nov 5, 2026Fuhao Li, Wenxuan Song, Qizhou Huang +7VLA Model TrainingSpatial Grounding for VLA Models

  2. SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments

    Jul 22, 2026Yang Xu, Gurpreet Singh Mukker, Raymond Wang +3Robotic GraspingLanguage-Conditioned Robot Manipulation

  3. Gripper-aware Vision Language Action Models

    Aug 25, 2026Hanyi Zhang, Zihong Luo, Tianyu Li +16Vision-Language-Action ModelsVLMs for Robotics