Dialogue based Interactive Explanations for Safety Decisions in Human Robot Collaboration

Yifan Xu; Xiao Zhan; Akilu Yunusa Kaltungo; Ming Shan Ng; Tsukasa Ishizawa; Kota Fujimoto; Clara Cheung

cs.ROApr 7, 2026

Dialogue based Interactive Explanations for Safety Decisions in Human Robot Collaboration

Authors: Yifan Xu, Xiao Zhan, Akilu Yunusa Kaltungo, Ming Shan Ng, Tsukasa Ishizawa, Kota Fujimoto, Clara Cheung

Organizations: Department of Civil Engineering and Management, Faculty of Science and Engineering, The University of Manchester, Manchester, United Kingdom · VRAIN, Universitat Polit`ecnica de Val`encia, Valencia, Spain & Department of Engineering, University of Cambridge, Cambridge, United Kingdom · Department of Mechanical and Aerospace Engineering, Faculty of Science and Engineering, The University of Manchester, Manchester, United Kingdom · Center for the Possible Futures, Kyoto Institute of Technology, Kyoto, Japan · Institute of Industrial Science, The University of Tokyo, Japan · Graduate School of Frontier Sciences, The University of Tokyo, Japan

Abstract

As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety decisions intelligible to human collaborators. In human robot collaboration (HRC), behaviours such as stopping or switching modes are often triggered by internal safety constraints that remain opaque to nearby workers. We present a dialogue based framework for interactive explanation of safety decisions in HRC. The approach tightly couples explanation with constraint based safety evaluation, grounding dialogue in the same state and constraint representations that govern behaviour selection. Explanations are derived directly from the recorded decision trace, enabling users to pose causal ("Why?"), contrastive ("Why not?"), and counterfactual ("What if?") queries about safety interventions. Counterfactual reasoning is evaluated in a bounded manner under fixed, certified safety parameters, ensuring that interactive exploration does not relax operational guarantees. We instantiate the framework in a construction robotics scenario and provide a structured operational trace illustrating how constraint aware dialogue clarifies safety interventions and supports coordinated task recovery. By treating explanation as an operational interface to safety control, this work advances a design perspective for interactive, safety aware autonomy in HRC.

Figures & tables

User Question	Safety Grounded Explanation Mechanism
Why did you stop?	The robot points to the safety constraint in $C_{t}$ that directly triggered the current behavior $u_{t}$ (e.g., the worker entered the 1.5 m safety zone).
Why didn’t you continue lifting?	The robot considers the alternative behavior and explains which safety parameter in $P$ would be violated if that behavior were executed.
What if I step back?	The robot evaluates the proposed change by constructing a hypothetical safety state $S_{t}^{\prime}$ , recomputing active constraints, and explaining whether a different behavior becomes feasible or remains blocked.

TABLE I: Safety grounded dialogue query types and their corresponding explanation mechanisms derived from the decision trace

Panel of Figure 2 — Fig. 1: Safety grounded dialogue explanation pipeline. Queries (e.g., “Why did you stop?”, “Why not continue?”, “What if I move closer?”) are classified into Why , Why-not , or What-if . Explanations are grounded in the recorded decision state $D_{t}=\{S_{t},u_{t},C_{t}\}$ . Counterfactual queries form a hypothetical state $S_{t}^{\prime}$ and re-evaluate constraints ( $C_{t}^{\prime}$ ) within certified safety limits $P$ .

Fig. 2: Construction environment schematic. A mobile manipulator transports a steel beam in a shared workspace with a human worker and a forklift. Safety envelopes include a proximity constraint $d_{\min}$ (dashed circle around the robot) and a visibility constraint defined by a minimum confidence level $v_{\min}$ (illustrated within the worker region). The forklift creates an occluded zone that reduces sensing reliability, potentially activating the visibility constraint.

Panel of Figure 4 — Fig. 3: Dialogue-based safety in the construction scenario.

Constraint Condition (over $S_{t}$ )	Selected Behavior
$d(H_{t},R_{t})<d_{\min}$	$u_{t}=\texttt{stop}$
$\texttt{visibility}(E_{t})<v_{\min}$	$u_{t}=\texttt{pause}$
$\texttt{worker\_in\_guidance\_zone}(H_{t})$	$u_{t}=\texttt{manual}$

TABLE II: Representative safety constraints in the prototype.

Explore similar work

Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues
Mar 8, 2026Zeyu Fang, Yuxin Lin, Cheng Liu +6Human-Robot Collaboration Robot Task Planning
Department of Electrical and Computer Engineering, George Washington University · the Department of Electrical and Computer Engineering, Northeastern University · the Department of Mechanical and Aerospace Engineering, George Washington University
SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration
Sep 17, 2026Yisen Li, Hao Zhang, Ruize Geng +3Safe RL Robot Safety
University of Texas at Arlington · Carnegie Mellon University
Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control
Mar 11, 2026Jake Gonzales, Kazuki Mizuta, Karen Leung +1Human-Robot Interaction Safe Robot Navigation
University of Washington, Department of Electrical and Computer Engineering · University of Washington, Department of Aeronautics and Astronautics

Mar 8, 2026J/K move · Enter open · S save

Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues

Zeyu Fang, Yuxin Lin, Cheng Liu, Beomyeol Yu+5

Department of Electrical and Computer Engineering, George Washington University · the Department of Electrical and Computer Engineering, Northeastern University · the Department of Mechanical and Aerospace Engineering, George Washington University

Human-Robot Collaboration Robot Task Planning Human-Robot Interaction

Open paper AskPDF arXiv

Effective human-robot collaboration in open-world environments requires joint planning under uncertainty about the task, the environment, and the human teammate. Communication is the most direct means of resolving such uncertainty, yet most existing systems support only one-way communication: robots listen and act, treating humans as passive supervisors rather than conversational teammates capable of two-way dialogue. We propose a unified human-robot joint planning system in which the robot actively resolves uncertainty through two complementary communication channels. When uncertainty is decision-critical, an uncertainty-mitigation joint planning module engages the human in clarification dialogue: it grounds ambiguous instructions via an LLM-assisted active elicitation mechanism, enumerates traversability hypotheses through a hypothesis-augmented A* search, and computes a cost-optimal querying policy via dynamic programming, so that the robot asks only the questions whose answers actually matter for the plan. When explicit dialogue is unnecessary or impractical, a real-time intent-aware collaboration module instead reads implicit, nonverbal cues, maintaining a probabilistic belief over the human's latent task intent from spatial and directional signals to enable coordination-aware task selection without any communication overhead. We validate the proposed system in both Gazebo simulations and real-world UAV deployments, integrated with a voice dialogue interface and a Vision-Language Model (VLM)-based 3D semantic perception pipeline. Experimental results show that cost-optimal clarification dialogue cuts the interaction cost by 51.9% while maintaining a 100% task success rate, and implicit intent reading reduces the cooperative task execution time by 25.4% compared to the baselines.

Abstract

Explore similar work

Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues

SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration

Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control