Pack It In: Packing into Partially Filled Containers through Contact
David Mackenzie Charles Russell, Zisong Xu, Maximo A. Roa, Mehmet R Dogar
AI summary
Problem
Traditional bin-packing systems assume collision-free insertion into empty or sparsely filled containers, but real-world warehouse containers are often partially filled and crowded, making standard planning fail without physical interaction.
Approach
The system uses a physics-aware perception module to track occluded objects, a placement planner to identify feasible target poses, and a contact-based trajectory optimizer within a model predictive controller to simultaneously displace clutter and insert new items.
Key results
- Formulated packing through clutter as a contact-based trajectory optimization problem
- Developed a physics-informed placement planner that minimizes scene disturbance
- Integrated trajectory optimization with MPC and physics-aware perception for robust real-robot execution
- Validated successful packing in highly cluttered containers through extensive real-robot experiments
Why it matters
Enables warehouse automation robots to handle realistic, crowded stowing tasks without specialized hardware or perfect pre-packing, bridging the gap between simulation and real-world logistics.
Abstract
The automation of warehouse operations is crucial for improving productivity and reducing human exposure to hazardous environments. One operation frequently performed in warehouses is bin-packing where items need to be placed into containers, either for delivery to a customer, or for temporary storage in the warehouse. Whilst prior bin-packing works have largely been focused on packing items into empty containers and have adopted collision-free strategies, it is often the case that containers will already be partially filled with items, of- ten in suboptimal arrangements due to transportation about a warehouse. This paper presents a contact-aware packing approach that exploits purposeful interactions with previously placed objects to create free space and enable successful place- ment of new items. This is achieved by using a contact-based multi-object trajectory optimizer within a model predictive controller, integrated with a physics-aware perception system that estimates object poses even during inevitable occlusions, and a method that suggests physically-feasible locations to place the object inside the container.