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

Robot social navigation is influenced by human preferences andenvironment-specific scenarios such as elevators and doors, thus necessitatingend-user adaptability. State-of-the-art approaches to social navigation fallinto two categories: model-based social constraints and learning-basedapproaches. While effective, these approaches have fundamental limitations --model-based approaches require constraint and parameter tuning to adapt topreferences and new scenarios, while learning-based approaches require rewardfunctions, significant training data, and are hard to adapt to new socialscenarios or new domains with limited demonstrations. In this work, we proposeIterative Dimension Informed Program Synthesis (IDIPS) to address theselimitations by learning and adapting social navigation in the form ofhuman-readable symbolic programs. IDIPS works by combining program synthesis,parameter optimization, predicate repair, and iterative human demonstration tolearn and adapt model-free action selection policies from orders of magnitudeless data than learning-based approaches. We introduce a novel predicate repairtechnique that can accommodate previously unseen social scenarios orpreferences by growing existing policies. We present experimental resultsshowing that IDIPS: 1) synthesizes effective policies that model userpreference, 2) can adapt existing policies to changing preferences, 3) canextend policies to handle novel social scenarios such as locked doors, and 4)generates policies that can be transferred from simulation to real-world robotswith minimal effort.

Iterative Program Synthesis for Adaptable Social Navigation