analiza aiqbench
PhyRoGen addresses the data scarcity bottleneck in robot manipulation by using procedural content generation to automatically create synthetic puzzles with complex interlocking dependencies. This framework enables the rapid generation of solvable benchmarks for sampling-based planning algorithms, facilitating the development of robust foundation models for assembly and disassembly tasks. The approach effectively bridges the gap between simulation and physical reality, as validated by successful manipulation in a KUKA LBR iiwa simulation environment.
PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation
arXiv:2606.06569v1 Announce Type: new Abstract: Robot manipulation of physical puzzles is important for automatic assembly and disassembly tasks. However, to enable robots to solve physical puzzles, manipulation skills need to be learned, which requires large training datasets, the generation of which is often time consuming and tedious. To overcome this problem, we propose the Physical Robot Manipulation Puzzle Generation framework (PhyRoGen), which leverages procedural content generation (PCG) for automated generation of synthetic datasets of manipulation puzzles. PhyRoGen is a general-purpose puzzle generator, which can generate physical puzzles with interlocking object dependencies, where one articulated object must be manipulated before another can be moved. Based upon PhyRoGen, we define six concrete generators which we use to generate 24 physical puzzles. By using a benchmarking framework, we are able to solve all puzzles in 1 to 300 seconds using sampling-based planning algorithms. Finally, we demonstrate that every generated puzzle is manipulatable by using a KUKA LBR iiwa robot in a physical simulation. This shows that our framework is able to procedurally generate unique, solvable robot manipulation puzzles, which is a crucial ingredient to benchmark manipulation algorithms and to develop robust foundation models.
Abstract:Robot manipulation of physical puzzles is important for automatic assembly and disassembly tasks. However, to enable robots to solve physical puzzles, manipulation skills need to be learned, which requires large training datasets, the generation of which is often time consuming and tedious. To overcome this problem, we propose the Physical Robot Manipulation Puzzle Generation framework (PhyRoGen), which leverages procedural content generation (PCG) for automated generation of synthetic datasets of manipulation puzzles. PhyRoGen is a general-purpose puzzle generator, which can generate physical puzzles with interlocking object dependencies, where one articulated object must be manipulated before another can be moved. Based upon PhyRoGen, we define six concrete generators which we use to generate 24 physical puzzles. By using a benchmarking framework, we are able to solve all puzzles in 1 to 300 seconds using sampling-based planning algorithms. Finally, we demonstrate that every generated puzzle is manipulatable by using a KUKA LBR iiwa robot in a physical simulation. This shows that our framework is able to procedurally generate unique, solvable robot manipulation puzzles, which is a crucial ingredient to benchmark manipulation algorithms and to develop robust foundation models.
Robotics (cs.RO)
arXiv:2606.06569 [cs.RO]
(or arXiv:2606.06569v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.06569 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 276 cuvinte
Subiecte conexe
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization
arXiv · 5 sept. 2026
FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
arXiv · 17 aug. 2026
Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation
arXiv · 17 sept. 2026
ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding
arXiv · 3 nov. 2026