cs.RONov 1, 2026

When to Probe and When to Act: Clarity-Aware Risk-Adaptive Control for Interactive Driving

Authors: Youran Wang, Devodita Chakravarty, Yiwei Lyu

Organizations: the Departments of Computer Sciences and Mathematics, University of Wisconsin–Madison, USA. · the Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, India. · the Department of Computer Science and Engineering, Texas A&M University, USA.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Safe navigation in interactive traffic requires autonomous vehicles to reason about unobservable human characteristics and the reciprocal nature of multi-agent interactions. Traditional architectures often decouple prediction from planning, leading to the "Frozen Robot Problem" or unsafe maneuvers under high ambiguity because they treat risk assessment and information acquisition as independent objectives. We argue that the notion of safety should not remain static but must instead dynamically co-evolve with the system's internal confidence: the robot should actively clarify ambiguity when necessary while also recognizing the diminishing returns of information, and naturally transition toward task execution. We introduce a unified belief-space Model Predictive Control (MPC) framework that couples multistep information planning with a clarity-adaptive Conditional Value-at-Risk (CVaR) barrier mechanism. By treating clarity, a scalar informational state, as an explicit planning variable, the controller co-designs its probing strategy with its safety specification, tightening conservatism under high ambiguity and relaxing constraints as confidence improves. We further provide a performance analysis showing that the cost of information seeking and the expected planning-cost gap to a controller that knows the true human characteristic are bounded by residual ambiguity and solver error. We evaluate the framework in lane-merging and unsignalized-intersection scenarios against representative interactive-planning baselines. Across 5,000 simulations, the proposed method achieves the highest success rates (94.6% and 93.2%) and the lowest collision rates (1.2% and 1.4%) among the compared methods, providing a principled foundation for robust decision-making in human-centric environments.

Figures & tables

Fig. 1 : Timestep-by-timestep overview of the proposed framework executing an unsignalized intersection crossing. Yellow and black denote the ego and human-driven vehicles, respectively; translucent silhouettes show past positions. Each row presents vehicle trajectories, the belief over the human characteristic θ\theta summarized over cooperative, neutral, and aggressive regions, the safety-margin distribution with lower-tail CVaR0.05\mathrm{CVaR}_{0.05} , clarity βk\beta_{k} , and control effort. At t1=0.0t_{1}=0.0 s, the ego approaches the intersection with a nearly uniform belief over θ\theta and a broad safety-margin distribution. Low clarity yields a large safety demand hsafe+κ(1/βk−1)h_{\text{safe}}+\kappa(1/\beta_{k}-1) in Eq. ( 7 ). At t2=1.3t_{2}=1.3 s, a cautious forward probe is followed by a shift toward an aggressive characteristic. The safety-margin distribution narrows and shifts left as the vehicles approach the conflict region, while clarity and control effort increase. At t3=2.6t_{3}=2.6 s, the belief further favors an aggressive characteristic. Increasing clarity reduces both the additional safety buffer and the information penalty Φ(βk)=1−βk\Phi(\beta_{k})=1-\beta_{k} , supporting a shift toward task execution. At t4=3.9t_{4}=3.9 s, the belief over θ\theta is more concentrated and the safety-margin distribution becomes sharper as the crossing progresses. At t5=5.5t_{5}=5.5 s, the ego has cleared the intersection, with a narrow predicted safety-margin distribution and reduced control effort. The sequence illustrates how evolving belief confidence jointly shapes information-seeking and safety conservatism, supporting a transition from cautious probing to task execution without explicit mode switching.
Fig. 2 : Qualitative lane-merging comparison in a selected episode. Faded vehicles indicate historical poses, while solid vehicles show the states at lane-change completion. The proposed method is the only method that merges ahead of the cooperative human driver in this episode, achieving the shortest task completion time of 5.4 s. RA-MPPI, AIG-MPC, D-MPPI, and ID-SMPC merge behind the human, completing the task in 6.1 s, 5.8 s, 6.4 s, and 5.9 s, respectively.
MethodSuccess Rate ↑\uparrowCollision Rate ↓\downarrowAverage Time (s) ↓\downarrowClarity ↑\uparrowWorst-tail CVaR 0.05 Margin (m) ↑\uparrowInformation Gain (nats) ↑\uparrowControl Effort ↓\downarrowSolver Time (s) ↓\downarrow
Lane Merge
Ours94.6%\mathbf{94.6\%}1.2%\mathbf{1.2\%}5.968±0.4635.968\pm 0.4630.841±0.082\mathbf{0.841\pm 0.082}1.5091.5090.581±0.313\mathbf{0.581\pm 0.313}1.000±0.4681.000\pm 0.4680.320.32
D-MPPI92.6%92.6\%1.4%1.4\%5.500±0.731\mathbf{5.500\pm 0.731}0.690±0.1030.690\pm 0.1030.8130.8130.190±0.3520.190\pm 0.3520.690±0.1190.690\pm 0.1190.08\mathbf{0.08}
AIG-MPC86.6%86.6\%3.0%3.0\%5.718±0.1825.718\pm 0.1820.616±0.0000.616\pm 0.000−3.024-3.0240.188±0.2300.188\pm 0.2300.094±0.027\mathbf{0.094\pm 0.027}1.241.24
RA-MPPI85.6%85.6\%3.2%3.2\%6.059±0.5026.059\pm 0.5020.650±0.0570.650\pm 0.0572.092\mathbf{2.092}0.078±0.1930.078\pm 0.1931.054±0.2101.054\pm 0.2100.540.54
ID-SMPC91.4%91.4\%1.6%1.6\%5.726±0.1945.726\pm 0.1940.616±0.01780.616\pm 0.0178−2.518-2.5180.122±0.2520.122\pm 0.2520.810±0.6860.810\pm 0.6860.820.82
TABLE I : Quantitative comparison across lane-merge and unsignalized-intersection scenarios (500 runs per method per scenario). The proposed method achieves the highest success rates (94.6% and 93.2%) and lowest collision rates (1.2% and 1.4%), respectively, together with the highest mean clarity and information gain in both scenarios. D-MPPI has the shortest completion times, while AIG-MPC uses the least control effort. RA-MPPI achieves the largest CVaR margin in lane merging, whereas the proposed method achieves the largest margin at intersections.
Fig. 3 : Behavioral comparison across lane-merge runs (mean ±\pm std). (a) Task progress : all methods achieve comparable route progress. (b) Clarity : the proposed method reaches higher reference-observer clarity than the baselines. (c) True safety margin : mean margins are initially similar but diverge near the merge region; the proposed method maintains a positive mean margin, while several baselines exhibit greater variability or reduced clearance. (d) Information gain : the proposed method exhibits a pronounced early peak followed by diminishing information gain as clarity increases, consistent with an early emphasis on information acquisition followed by task execution.
MetricCertainty-EqFixed CVaRInfo-SeekingOurs
Success Rate78.4%78.4\%86.7%86.7\%88.2%88.2\%92.9%\mathbf{92.9\%}
Collision Rate5.6%5.6\%0.5%\mathbf{0.5\%}2.1%2.1\%0.9%0.9\%
Average Time (s)5.01±1.88\mathbf{5.01\pm 1.88}7.92±2.317.92\pm 2.316.21±2.046.21\pm 2.045.63±1.765.63\pm 1.76
Mean Final Clarity β↑\beta\uparrow0.61±0.090.61\pm 0.090.58±0.050.58\pm 0.050.72±0.140.72\pm 0.140.85±0.06\mathbf{0.85\pm 0.06}
Mean CVaR Safety Slack ↑\uparrow−0.12±0.21-0.12\pm 0.210.41±0.10\mathbf{0.41\pm 0.10}0.18±0.190.18\pm 0.190.32±0.120.32\pm 0.12
TABLE II : Ablation study across all scenarios (2,880 runs). The proposed method achieves the highest success rate (92.9%) and mean final clarity ( 0.85±0.060.85\pm 0.06 ). Fixed CVaR attains the lowest collision rate (0.5%) but the longest average time ( 7.92±2.317.92\pm 2.31 s). Certainty-Eq is fastest ( 5.01±1.885.01\pm 1.88 s) but has the highest collision rate (5.6%) and negative mean CVaR safety slack, indicating repeated safety margin violations.
Fig. 4 : CVaR barrier value versus clarity βk\beta_{k} for each ablation variant, across all simulation runs. The proposed method concentrates in the high-clarity region while maintaining positive barrier values, illustrating the combination of belief refinement and safety preservation.
More in this topic

Dual Control

See all 8 papers

Explore similar work

CardsList
Feb 16, 2026

Multimodal Belief-Space Covariance Steering with Active Probing and Influence for Interactive Driving

Autonomous driving in complex traffic requires reasoning under uncertainty. Common approaches rely on prediction-based planning or risk-aware control, but these are typically treated in isolation, limiting their ability to capture the coupled nature of action and inference in interactive settings. This gap becomes especially critical in uncertain scenarios, where simply reacting to predictions can lead to unsafe maneuvers or overly conservative behavior. Our central insight is that safe interaction requires not only estimating human behavior but also shaping it when ambiguity poses risks. To this end, we introduce a hierarchical belief model that structures human behavior across coarse discrete intents and fine motion modes, updated via Bayesian inference for interpretable multi-resolution reasoning. On top of this, we develop an active probing strategy that identifies when multimodal ambiguity in human predictions may compromise safety and plans disambiguating actions that both reveal intent and gently steer human decisions toward safer outcomes. Finally, a runtime risk-evaluation layer based on Conditional Value-at-Risk (CVaR) ensures that all probing actions remain within human risk tolerance during influence. Our simulations in lane-merging and unsignaled intersection scenarios demonstrate that our approach achieves higher success rates and shorter completion times compared to existing methods. These results highlight the benefit of coupling belief inference, probing, and risk monitoring, yielding a principled and interpretable framework for planning under uncertainty.

Devodita Chakravarty, John Dolan, Yiwei Lyu

Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, India · Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA

Risk-Sensitive PlanningAutonomous Driving PlanningDecision-Making under UncertaintyBelief-Space PlanningActive Perception
AskPDF
Jun 8, 2026

Uncertainty-Aware Motion Planning for Autonomous Driving in Mixed Traffic Environment

In mixed-traffic environments where autonomous and human-driven vehicles may co-exist, motion planning for autonomous vehicles requires anticipating the future behaviors of surrounding human drivers. Existing reinforcement learning-based methods generally directly incorporate the predicted human intents into the observation to enable a proactive planning. However, human intent is inherently uncertain due to the behavioral diversity, perception noise, and partial observability. Treating predicted intends as deterministic states can result in unsafe decisions for autonomous vehicles. To address this problem, we propose Uncertainty-Aware Motion Planning (UAMP), which incorporates uncertainty in human intent prediction for AV decision-making. Specifically, UAMP first introduces a proximity-aware uncertainty estimator to quantify the interaction-conditioned intent uncertainty and constructs an uncertainty-guided joint intent distribution over surrounding human-driven vehicles. Within this uncertainty set, UAMP further introduces Uncertainty-Calibrated Value Learning (UCVL) to correct value function learning biases arising from directly incorporating uncertain human intent predictions into the observation. Extensive experiments in various mixed-traffic scenarios show that UAMP significantly improves safety and driving comfort, while maintaining traffic efficiency compared with existing approaches. The code is released at https://anonymous.4open.science/r/UAMP-5638.

Ming Cheng, Hao Chen, Ziyi Yang +2

Central South University · City University of Macau

Safe Motion PlanningMotion PlanningAutonomous Driving PlanningRL for Autonomous Driving
AskPDF
Mar 11, 2026

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

In this paper, we present a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control to provide formal safety guarantees while considering complex human behavior. The approach uses conformal risk control to quantify and control the prediction errors in CBF safety values and establishes formal guarantees on the probability of constraint satisfaction during interaction. We introduce an algorithm that dynamically adjusts the safety margins produced by conformal risk control based on the current interaction context. Through experiments on human-robot navigation scenarios, we demonstrate that our approach significantly reduces collision rates and safety violations as compared to baseline methods while maintaining high success rates in goal-reaching tasks and efficient control. The code, simulations, and other supplementary material can be found on the project website: https://jakeagonzales.github.io/crc-cbf-website/.

Jake Gonzales, Kazuki Mizuta, Karen Leung +1

University of Washington, Department of Electrical and Computer Engineering · University of Washington, Department of Aeronautics and Astronautics

Human-Robot InteractionSafe Robot NavigationRobot Collision AvoidanceControl Barrier FunctionsConformal Risk Control
AskPDF