Workshop papers at ICRA 2026 and CVPR 2026
Consent chain degradation in embodied multi-agent systems (ICRA WoRoBet) and belief-aware privileged distillation for autonomous driving (CVPR WAD).
When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability
Extends Guided Soft Actor-Critic with Belief-Aware GSAC, which scales the privileged-distillation coefficient by ensemble disagreement in a driving POMDP.
Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics
Introduces consent chain degradation: the way the specificity, validity and scope of human consent weaken as authority passes through chains of delegation among embodied agents.
Agent-Based Reinforcement Learning for Geochemical Control in Geothermal Energy Systems
Research area: AI for Geoscience & Energy, Reinforcement Learning & Autonomous Systems.
fusun-servin-tut-hakl%C4%B1d%C4%B1r
Bidirectional Human Interactive AI Framework for Social Robot Navigation
Research area: Reinforcement Learning & Autonomous Systems.
tuba-girgin
Prediction of Lifted Weight Category Using EEG Equipped Headgear
Research area: AI for Health, Reinforcement Learning & Autonomous Systems.
sencer-melih-deniz
Cloud Assisted Connected and Automated Mobility System Architecture Design and Experimental Verification: The 5G-MOBIX Autonomous Truck Routing Use Case
Demonstrates the use of 5G networks for a cloud-assisted connected and automated mobility service in the EU H2020 5G-MOBIX project, with preliminary field tests of the autonomous …
tahir-sar%C4%B1
Autonomous Driving Systems for Decision-Making Under Uncertainty Using Deep Reinforcement Learning
Research area: Reinforcement Learning & Autonomous Systems.
Deep Reinforcement Learning for Partially Observable Markov Decision Processes
Research area: Reinforcement Learning & Autonomous Systems.
Guided Soft Actor Critic: A Guided Deep Reinforcement Learning Approach for Partially Observable Markov Decision Processes
Introduces Guided Soft Actor-Critic (GSAC), in which a guidance module steers Soft Actor-Critic during training to cope with partial observability, improving sample efficiency and …