CORTEXA
← Browse
arxivcs.RO2026-07-16

Risk-Aware Preference Learning for Stochastic Outcomes

Yi-Shiuan Tung, Yuni Wu, Wei Jiang, Alessandro Roncone, Bradley Hayes

Learning reward functions from human preferences is a widely used approach for aligning robot behavior with user expectations in human-robot interaction. Most existing approaches assume that humans evaluate uncertain outcomes using expected utility (EU), aggregating outcome utilities linearly with their probabilities. However, behavioral evidence shows that humans are systematically risk-sensitive, overweighting rare negative events and exhibiting loss aversion. We study the consequences of this mismatch in social robot navigation, where safety-critical outcomes (e.g., collisions) are rare but highly consequential. We compare EU with Cumulative Prospect Theory (CPT), a nonlinear model of human decision-making, within a Bradley-Terry preference learning framework. Our preliminary experiments show that when preferences are generated by risk-sensitive users, CPT-based learners recover reward functions with substantially lower regret compared to EU-based learners. Our results highlight the importance of modeling human risk sensitivity when learning rewards from preferences over stochastic robot outcomes.

View free PDFSource page

Related papers

arxivcs.ROcs.AI2026-06-25

Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World Modeling

Daosheng Qiu, Haozhuang Chi, Hao Su, Shu Long, Xinyue Miao, Yongle Dong, et al.

Continuous driver monitoring in automated vehicles requires low-latency inference while avoiding unsafe decisions under uncertain driver states. Large vision-language models provide broad multimodal priors, but their latency and limited reliability in this setting make them unsui…

View free PDFSource page
arxivcs.RO2026-06-29Cited by 2

MOAR Planner: Multi-Objective and Adaptive Risk-Aware Path Planning for Infrastructure Inspection with a UAV

Louis Petit, Alexis Lussier Desbiens

The problem of autonomous navigation for UAV inspection remains challenging as it requires effectively navigating in close proximity to obstacles, while accounting for dynamic risk factors such as weather conditions, communication reliability, and battery autonomy. This paper int…

View free PDFSource page
arxivcs.RO2026-07-16

Risk-Aware Belief Control Barrier Functions over Random Finite Sets

Shaohang Han, Gang Chen, Yixi Cai, Ignacio Torroba, Ivan Stenius, Patric Jensfelt, et al.

Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertai…

View free PDFSource page
arxivcs.ROcs.MAeess.SY2026-07-16

Mixed-Agent Museum Tour Guide Design Improves Gendered Learning Outcomes and Visitor Preferences

Annette M. Masterson, Wonse Jo, Helena C. Sieh, Lionel P. Robert,, Dawn Tilbury

Robots are increasingly integrated into everyday contexts, including museums, where they can both entertain and educate visitors. To enhance visitor experience and engagement, we present a novel mixed-agent tour guide system that combines a physical robot with a projected virtual…

View free PDFSource page
arxivcs.AIcs.RO2026-07-31

LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

Manith Adikari, Bei Peng, Samuele Vinanzi, Angelo Cangelosi

Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, competing objectives, such as performance versus efficiency, where ground-truth reward functions are…

View free PDFSource page
arxivcs.RO2026-07-14

Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences

Taehyung Kim, Gwangmo Lee, Minjun Chang, Sunghyun Lim, Jongeun Choi

Aligning robot policies with human preferences is essential for deployment to diverse end users. In per-user alignment approach, preference feedback is often sparse, so learning becomes unstable and vulnerable to human preference noise, and a growing number of individualized poli…

View free PDFSource page