arXiv subjects

Yi-Shiuan Tung

Publications and source records attributed to Yi-Shiuan Tung.

9 recordsLinked to original sources

arXiv2026

Counterfactual Reasoning and Environment Design for Active Preference Learning

For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods often struggle to explore the full trajectory space and fail to identify informative queries, particularly in long-horizon tasks. We propose CRED, a trajectory generation method for APL that improves reward estimation by jointly optimizing environment design and trajectory selection. CRED "imagines" new scenarios through environment design and uses counterfactual reasoning -- by sampling rewards from its current belief and asking "What if this reward were the true preference?" -- to generate a diverse and informative set of trajectories for ranking. Experiments in GridWorld and real-world navigation using OpenStreetMap data show that CRED improves reward learning and generalizes effectively across different environments.

cs.RO↗

arXiv2026

Risk-Aware Preference Learning for Stochastic Outcomes

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.

cs.RO↗

arXiv2026

Environment Design for Reliable Shared Autonomy with Probabilistic Guarantees

Shared autonomy enables humans and robots to collaboratively perform tasks by combining human input with autonomous assistance. Most prior work focuses on improving intent inference under a fixed environment, overlooking how workspace design itself affects inference difficulty. We observe that the physical arrangement of objects directly influences the separability of candidate goals under noisy user inputs. We formulate workspace design as an optimization problem and derive a probabilistic correctness guarantee under a bounded noise model. Through simulation experiments across multiple tabletop scenarios, we show that optimized layouts improve goal inference reliability and reduce ambiguity compared to baseline arrangements. We further demonstrate a real-world shared autonomy system that integrates the proposed inference framework. This highlights the role of environment design as a complementary axis for improving shared autonomy systems.

cs.RO↗

arXiv2026

CRED: Counterfactual Reasoning and Environment Design for Active Preference Learning

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach. These systems benefit strongly by being able to align their behavior to reflect human preferences and respond to corrections, but manually encoding this feedback is infeasible. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods sample from fixed trajectory sets or replay buffers that limit query diversity and often fail to identify informative comparisons. We propose CRED, a novel trajectory generation method for APL that improves reward inference by jointly optimizing environment design and trajectory selection to efficiently query and extract preferences from users. CRED "imagines" new scenarios through environment design and leverages counterfactual reasoning -- by sampling possible rewards from its current belief and asking "What if this were the true preference?" -- to generate trajectory pairs that expose differences between competing reward functions. Comprehensive experiments and a user study show that CRED significantly outperforms state-of-the-art methods in reward accuracy and sample efficiency and receives higher user ratings.

cs.RO↗

arXiv2024

PokeRRT: Poking as a Skill and Failure Recovery Tactic for Planar Non-Prehensile Manipulation

In this work, we introduce PokeRRT, a novel motion planning algorithm that demonstrates poking as an effective non-prehensile manipulation skill to enable fast manipulation of objects and increase the size of a robot's reachable workspace. We showcase poking as a failure recovery tactic used synergistically with pick-and-place for resiliency in cases where pick-and-place initially fails or is unachievable. Our experiments demonstrate the efficiency of the proposed framework in planning object trajectories using poking manipulation in uncluttered and cluttered environments. In addition to quantitatively and qualitatively demonstrating the adaptability of PokeRRT to different scenarios in both simulation and real-world settings, our results show the advantages of poking over pushing and grasping in terms of success rate and task time.

cs.RO↗

arXiv2024

Workspace Optimization Techniques to Improve Prediction of Human Motion During Human-Robot Collaboration

Understanding human intentions is critical for safe and effective human-robot collaboration. While state of the art methods for human goal prediction utilize learned models to account for the uncertainty of human motion data, that data is inherently stochastic and high variance, hindering those models' utility for interactions requiring coordination, including safety-critical or close-proximity tasks. Our key insight is that robot teammates can deliberately configure shared workspaces prior to interaction in order to reduce the variance in human motion, realizing classifier-agnostic improvements in goal prediction. In this work, we present an algorithmic approach for a robot to arrange physical objects and project "virtual obstacles" using augmented reality in shared human-robot workspaces, optimizing for human legibility over a given set of tasks. We compare our approach against other workspace arrangement strategies using two human-subjects studies, one in a virtual 2D navigation domain and the other in a live tabletop manipulation domain involving a robotic manipulator arm. We evaluate the accuracy of human motion prediction models learned from each condition, demonstrating that our workspace optimization technique with virtual obstacles leads to higher robot prediction accuracy using less training data.

cs.RO↗

arXiv2023

Improving Human Legibility in Collaborative Robot Tasks through Augmented Reality and Workspace Preparation

Understanding the intentions of human teammates is critical for safe and effective human-robot interaction. The canonical approach for human-aware robot motion planning is to first predict the human's goal or path, and then construct a robot plan that avoids collision with the human. This method can generate unsafe interactions if the human model and subsequent predictions are inaccurate. In this work, we present an algorithmic approach for both arranging the configuration of objects in a shared human-robot workspace, and projecting ``virtual obstacles'' in augmented reality, optimizing for legibility in a given task. These changes to the workspace result in more legible human behavior, improving robot predictions of human goals, thereby improving task fluency and safety. To evaluate our approach, we propose two user studies involving a collaborative tabletop task with a manipulator robot, and a warehouse navigation task with a mobile robot.

cs.RO↗

arXiv2022

Bilevel Optimization for Just-in-Time Robotic Kitting and Delivery via Adaptive Task Segmentation and Scheduling

Kitting refers to the task of preparing and grouping necessary parts and tools (or "kits") for assembly in a manufacturing environment. Automating this process simplifies the assembly task for human workers and improves efficiency. Existing automated kitting systems adhere to scripted instructions and predefined heuristics. However, given variability in the availability of parts and logistic delays, the inflexibility of existing systems can limit the overall efficiency of an assembly line. In this paper, we propose a bilevel optimization framework to enable a robot to perform task segmentation-based part selection, kit arrangement, and delivery scheduling to provide custom-tailored kits just in time - i.e., right when they are needed. We evaluate the proposed approach both through a human subjects study (n=18) involving the construction of a flat-pack furniture table and shop-flow simulation based on the data from the study. Our results show that the just-in-time kitting system is objectively more efficient, resilient to upstream shop flow delays, and subjectively more preferable as compared to baseline approaches of using kits defined by rigid task segmentation boundaries defined by the task graph itself or a single kit that includes all parts necessary to assemble a single unit.

cs.RO↗

arXiv2022

PokeRRT: A Kinodynamic Planning Approach for Poking Manipulation

This work introduces PokeRRT, a novel motion planning algorithm that demonstrates poking as an effective non-prehensile manipulation skill to enable fast manipulation of objects and increase the size of a robot's reachable workspace. Our qualitative and quantitative results demonstrate the advantages of poking over pushing and grasping in planning object trajectories through uncluttered and cluttered environments.

cs.RO↗