English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Constrained robot motion planning is a ubiquitous need for robots interactingwith everyday environments, but it is a notoriously difficult problem to solve.Many sampled points in a sample-based planner need to be rejected as they falloutside the constraint manifold, or require significant iterative effort tocorrect. Given this, few solutions exist that present a constraint-satisfyingtrajectory for robots, in reasonable time and of low path cost. In this work,we present a transformer-based model for motion planning with task spaceconstraints for manipulation systems. Vector Quantized-Motion PlanningTransformer (VQ-MPT) is a recent learning-based model that reduces the searchspace for unconstrained planning for sampling-based motion planners. We proposeto adapt a pre-trained VQ-MPT model to reduce the search space for constraintplanning without retraining or finetuning the model. We also propose to updatethe neural network output to move sampling regions closer to the constraintmanifold. Our experiments show how VQ-MPT improves planning times and accuracycompared to traditional planners in simulated and real-world environments.Unlike previous learning methods, which require task-related data, our methoduses pre-trained neural network models and requires no additional data fortraining and finetuning the model making this a \textit{one-shot} process. Wealso tested our method on a physical Franka Panda robot with real-world sensordata, demonstrating the generalizability of our algorithm. We anticipate thisapproach to be an accessible and broadly useful for transferring learned neuralplanners to various robotic-environment interaction scenarios.

Zero-Shot Constrained Motion Planning Transformers Using Learned Sampling Dictionaries