Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object collisions.
We propose APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon planning. APIVOT learns to leverage language for semantic reasoning while using visual thoughts as imagined future states for internal verification of geometric feasibility. In long-horizon kitchen tasks, APIVOT outperforms general-purpose VLMs and prior planning frameworks, achieving the largest gains in spatially constrained settings.
We find that APIVOT learns meaningful modality selection behavior, demonstrating that adaptive interleaving of vision-language thoughts improves both planning success and reasoning efficiency.
Blogger's Review: The design of APIVOT not only breaks through traditional limitations in robot planning but also showcases the deep integration of language and visual information, significantly enhancing the adaptability and efficiency of robots in complex environments. This approach will provide new insights and directions for future intelligent robotic systems.