PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Researchers introduced PackLab, a framework for developing, training, and evaluating multimodal large language models (MLLMs) in robotic bin packing, addressing the long-horizon sequential decision-making problem where each object placement affects the space available for subsequent packing. The framework targets the limitations of existing methods, which rely primarily on hand-crafted geometric heuristics that optimize predefined objectives or reinforcement learning policies. PackLab aims to support MLLM-based approaches to the task.

Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Existing methods primarily rely on hand-crafted geometric heuristics that optimize predefined objectives or reinforcement learning policies learned throu