Search papers, labs, and topics across Lattice.
This paper introduces a robotic manipulator system for mixed palletizing, combining reinforcement learning (PMP-RL) for stable box placement and a configuration-space motion planning network (CMPNet) for collision-free robot movement. PMP-RL maximizes pallet volume utilization with stability-enhancing reward functions, while CMPNet predicts motion trajectories in 3D configuration space, imitating expert-level paths for real-time motion generation. Experiments in simulation and real-world environments demonstrate the system's ability to handle complex palletizing tasks with high efficiency and stability.
Stack boxes like a pro: this robotic system uses reinforcement learning and motion planning to solve mixed palletizing in real-world warehouses.
Palletizing, also known as the 3D bin packing problem, is important for optimizing space utilization and automating packing processes, especially in the logistics industry. In practice, handling mixed palletizing scenarios, where a variety of boxes of different sizes are received in real time, is considerably challenging. Existing methods for solving the mixed palletizing problem often overlook practical constraints encountered in real-world applications, such as those pertaining to stability and robustness. In this paper, we propose a practical mixed palletizing manipulator system designed for structured real-world warehouse environments. Our manipulator system has two main components: a practical mixed palletizing model based on reinforcement learning (PMP-RL), which can facilitate stable and efficient box placing, and a configuration-space motion planning network (CMPNet), which can help achieve robust and efficient collision-free robot movement. The PMP-RL model is designed to maximize the pallet volume utilization while incorporating practical reward functions that enhance stability. CMPNet is used to directly predict motion trajectories in a 3D configuration space, and it facilitates real-time motion generation by effectively imitating expert-level paths. Overall, the manipulator system, comprising an automated conveyor belt, a camera-based recognition system, the PMP-RL model, and CMPNet, provide a robust and practical framework for mixed palletizing. Experiments conducted via simulations and in real-world environments have shown that the manipulator system can handle complex palletizing tasks with high efficiency and high stability. Note to Practitioners—This work introduces a practical robotic palletizing system that stacks boxes of various sizes in real time, addressing common issues such as unstable stacking and inefficient robot motion. By combining reinforcement learning for box placement with fast, collision-free motion planning, the system improves efficiency and reliability in warehouse automation. The approach operates in real-world settings using standard hardware like conveyor belts, cameras, and robot arms, and can reduce manual workload. The current implementation is designed for structured warehouse environments with rigid cuboidal boxes, which allows efficient perception and reliable placement decisions. While this assumption simplifies deployment, it also limits direct applicability to irregular-shaped items or unstructured scenarios. Moreover, the present framework has been optimized for 3-DoF manipulators; extending it to higher-DoF robots may require additional consideration of computational efficiency in learning and motion planning. It is suitable for industrial use and can be extended to more complex environments through enhanced perception and manipulation modules, with further customization.
