eess.SYOct 15, 2025

Safe Driving in Occluded Environments

Authors: Zhuoyuan Wang, Tongyao Jia, Pharuj Rajborirug, Neeraj Ramesh, Hiroyuki Okuda, Tatsuya Suzuki, Soummya Kar, Yorie Nakahira

Organizations: Department of Electrical and Computer Engineering, Carnegie Mellon Universty · Faculty of Medicine, King Mongkut’s Institute of Technology Ladkrabang, Thailand · Department of Mechanical Systems Engineering, Nagoya University, Japan

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Ensuring safe autonomous driving in the presence of occlusions poses a significant challenge in its policy design. While existing model-driven control techniques based on set invariance can handle visible risks, occlusions create latent risks in which safety-critical states are not observable. Data-driven techniques also struggle to handle latent risks because direct mappings from risk-critical objects in sensor inputs to safe actions cannot be learned without visible risk-critical objects. Motivated by these challenges, in this paper, we propose a probabilistic safety certificate for latent risk. Our key technical enabler is the application of probabilistic invariance: It relaxes the strict observability requirements imposed by set-invariance methods that demand the knowledge of risk-critical states. The proposed techniques provide linear action constraints that confine the latent risk probability within tolerance. Such constraints can be integrated into model predictive controllers or embedded in data-driven policies to mitigate latent risks. The proposed method is tested using the CARLA simulator and compared with a few existing techniques. The theoretical and empirical analysis jointly demonstrate that the proposed methods assure long-term safety in real-time control in occluded environments without being overly conservative and with transparency to exposed risks.

Figures & tables

Fig. 1 : Visually occluded intersection scenario of interest.
Fig. 2 : CARLA Scenario Setup.
Fig. 3 : Estimation of safety probability Ψ(x)\mathbf{\Psi}(x) with grid discretization dxinit=2dx_{\text{init}}=2 for initial position and dvinit=0.5dv_{\text{init}}=0.5 for initial velocity. Blue curves show the typical vehicle trajectories under the proposed safe controller, with the blue dots as initial states.
Fig. 4 : Vehicle velocities of the proposed safe controller and baselines methods. Triangle indicates safely pass through the intersection. Square indicates collision with pedestrian.
Fig. 5 : Safety-efficiency trade-offs.
Control MethodSettings1−ϵ1-\epsilonPsafeP_{\text{safe}} ↑\uparrowt  (s)t\;(\mathrm{s}) ↓\downarrow
Proposed 0.90.9826.94
Worst-Case -155.49
Planning-basedxinit=−180mx_{\text{init}}=-180\mathrm{m}-0.9634.64
OA-MPCvinit=2m/sv_{\text{init}}=2\mathrm{m/s}-0.9438.29
TransFuser -0.5333.76
PID -132.68
TABLE I : Empirical safety probabilities and traveling time. ↑\uparrow and ↓\downarrow indicate larger or smaller values preferred, respectively.
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Fig. 6 : Visualization of the scenario and the corresponding processed sensor inputs for TransFuser [ 61 ] . (a) Birds’ eye view of the scenario. (b) HD map prediction. (c) Obstacle prediction. (d) LiDAR ground panel. (e) First-person view from the ego vehicle. (f) Predicted depth. (g) Predicted semantics.
Fig. 7 : Vehicle velocities of the proposed safe controller with different α\alpha . In all cases the vehicle safely pass through the intersection (indicated by the triangle).
α(h)\alpha(h)PsafeP_{\text{safe}} ↑\uparrowt  (s)t\;(\mathrm{s}) ↓\downarrow
0.05h0.05h0.9619.80
0.10h0.10h1.0020.95
0.20h0.20h1.0020.25
0.50h0.50h1.0022.05
1.00h1.00h0.9823.30
TABLE II : Empirical safety probability and average traveling time with different α\alpha . ↑\uparrow and ↓\downarrow indicate larger or smaller values preferred, respectively.
Control MethodSettings1−ϵ1-\epsilonPsafeP_{\text{safe}} ↑\uparrowt  (s)t\;(\mathrm{s}) ↓\downarrow
Proposed 0.95125.36
Worst-Case -146.98
Planning-basedxinit=−180mx_{\text{init}}=-180\mathrm{m}-0.9432.98
OA-MPCvinit=5m/sv_{\text{init}}=5\mathrm{m/s}-0.8641.60
TransFuser -0.5831.8
PID -0.713.16
TABLE III : Empirical safety probabilities and traveling time. ↑\uparrow and ↓\downarrow indicate larger or smaller values preferred, respectively.
Fig. 8 : Ego vehicle velocity under different pedestrian occurrence probabilities. In all cases the vehicle safely pass through the intersection (indicated by the triangle).
Fig. 9 : Safe control actions under different pedestrian occurrence probabilities.
More in this topic

Autonomous Driving

Autonomous driving develops vehicles that perceive road scenes, predict interactions, and plan and control safe movement with limited or no human input.

See all 536 papers

Explore similar work

CardsList

  1. Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments

    May 21, 2026Jie Jia, Yaofeng Su, Zeyu Bao +4Occlusion ReasoningAutonomous Driving Perception

    Fudan University, China · Tongji University, China

  2. Occlusion-Aware Contingency Safety-Critical Planning for Autonomous Driving

    Feb 10, 2025Lei Zheng, Rui Yang, Minzhe Zheng +3Safe Motion PlanningMotion Planning

    Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China · School of Engineering, Great Bay University, Dongguan 523000, China · Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology, Hong Kong SAR, China

  3. Hope for the Best, Prepare for the Worst: Occlusion-Aware Contingency Planning for Autonomous Vehicles

    Jul 3, 2026Truls Nyberg, Anna Gautier, Jana TumovaCollision AvoidanceOcclusion Reasoning

    KTH Royal Institute of Technology · Traton AB · Chalmers University of Technology +1