Results show that aligning planner-generated demonstrations with the pretraining distribution can make TAMP an effective source of data for VLA fine-tuning, and incorporate the pretraining distribution directly into TAMP trajectory generation.
Samrat Sahoo, Yi-Xuan Huang, Tom Silver· 1 citation· ⚡1
TANDEM (Tamp with As-Needed Demonstrations for Efficient Model fine-tuning), a system that combines TAMP with selective human teleoperation to collect demonstrations for tasks beyond the planner's capabilities, is presented.
Samrat Sahoo, Li Ji, Tom Silver et al.· 0 citations
This work finds that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success.
Matteo Merler, Bo-Wen Li, Josh Roy et al.· 1 citation
Robot Question Answering (RQA), a modular evaluation framework and RoboVista, a benchmark curated from real robotic systems, research papers, and expert annotations are proposed and physical robot experiments suggest strong correlation between RoboVista performance and real-world task execution.
