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

Task and Motion Planning (TAMP) approaches are effective at planninglong-horizon autonomous robot manipulation. However, it can be difficult toapply them to domains where the environment and its dynamics are not fullyknown. We propose to overcome these limitations by leveraging deep generativemodeling, specifically diffusion models, to learn constraints and samplers thatcapture these difficult-to-engineer aspects of the planning model. Theselearned samplers are composed and combined within a TAMP solver in order tofind action parameter values jointly that satisfy the constraints along a plan.To tractably make predictions for unseen objects in the environment, we definethese samplers on low-dimensional learned latent embeddings of changing objectstate. We evaluate our approach in an articulated object manipulation domainand show how the combination of classical TAMP, generative learning, and latentembeddings enables long-horizon constraint-based reasoning. We also apply thelearned sampler in the real world. More details are available athttps://sites.google.com/view/dimsam-tamp

DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability