analiza aiqbench
This research introduces COAD, a framework enabling constant-time motion planning for robotic manipulation by compressing solution libraries and using online adaptation techniques. By discretizing continuous task spaces into representative regions, the method achieves sub-millisecond query times while maintaining high success rates across various real-world scenarios. The work advances practical robotics efficiency without relying on large-scale offline storage of every possible trajectory.
CoAd: Constant-Time Planning for Continuous Goal Manipulation with Compressed Library and Online Adaptation
arXiv:2603.12488v2 Announce Type: replace Abstract: In many robotic manipulation tasks, the robot repeatedly solves motion-planning problems that differ mainly in the location of the goal object and its associated obstacle, while the surrounding workspace remains fixed. Prior works have shown that leveraging experience and offline computation can accelerate repeated planning queries, but they lack guarantees of covering the continuous task space and require storing large libraries of solutions. In this work, we present COAD, a framework that provides constant-time planning over a continuous goal-parameterized task space. COAD discretizes the continuous task space into finitely many Task Coverage Regions. Instead of planning and storing solutions for every region offline, it constructs a compressed library by only solving representative root problems. Other problems are handled through fast adaptation from these root solutions. At query time, the system retrieves a root motion in constant time and adapts it to the desired goal using lightweight adaptation modules such as linear interpolation, Dynamic Movement Primitives, or simple trajectory optimization. We evaluate the framework on various manipulators and environments in simulation and the real world, showing that COAD achieves substantial compression of the motion library while maintaining high success rates and sub-millisecond-level queries, outperforming baseline methods in both efficiency and path quality. The source code is available at https://github.com/elpis-lab/CoAd.
Abstract:In many robotic manipulation tasks, the robot repeatedly solves motion-planning problems that differ mainly in the location of the goal object and its associated obstacle, while the surrounding workspace remains fixed. Prior works have shown that leveraging experience and offline computation can accelerate repeated planning queries, but they lack guarantees of covering the continuous task space and require storing large libraries of solutions. In this work, we present COAD, a framework that provides constant-time planning over a continuous goal-parameterized task space. COAD discretizes the continuous task space into finitely many Task Coverage Regions. Instead of planning and storing solutions for every region offline, it constructs a compressed library by only solving representative root problems. Other problems are handled through fast adaptation from these root solutions. At query time, the system retrieves a root motion in constant time and adapts it to the desired goal using lightweight adaptation modules such as linear interpolation, Dynamic Movement Primitives, or simple trajectory optimization. We evaluate the framework on various manipulators and environments in simulation and the real world, showing that COAD achieves substantial compression of the motion library while maintaining high success rates and sub-millisecond-level queries, outperforming baseline methods in both efficiency and path quality. The source code is available at this https URL.
Robotics (cs.RO)
arXiv:2603.12488 [cs.RO]
(or arXiv:2603.12488v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2603.12488 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 · 301 cuvinte
Subiecte conexe
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Biological Superintelligence
LessWrong · 30 iul. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026