Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safe Driving in Occluded Environments

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

TL;DR

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.

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.

Safe Driving in Occluded Environments

TL;DR

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.

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.
Paper Structure (21 sections, 1 theorem, 23 equations, 9 figures, 3 tables, 3 algorithms)

This paper contains 21 sections, 1 theorem, 23 equations, 9 figures, 3 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Existing techniques for driving in occluded environments
  3. Problem Formulation
  4. Vehicle Dynamics and Nominal Control
  5. Interaction Model
  6. Occlusion Model
  7. Safety Specification
  8. Proposed Method
  9. Condition for Assuring Safety
  10. Risk Estimation
  11. Safe Control
  12. Experiments
  13. CARLA Setup
  14. Risk Probability Estimation
  15. Safe Control
  16. ...and 6 more sections

Key Result

Theorem 3

Consider systems eq:dynamics and eqn:interaction_update which forms eq:overall_dynamics. We assume the initial condition $X^{\text{all}}_0=x^{\text{all}}_0$ satisfies $\mathbb{P}(S|X^{\text{all}}_0=x^{\text{all}}_0)\geq 1-\epsilon$. If at each time $k$, the ego vehicle generates a control policy tha

Figures (9)

  • Figure 1: Visually occluded intersection scenario of interest.
  • Figure 2: CARLA Scenario Setup.
  • Figure 3: Estimation of safety probability $\mathbf{\Psi}(x)$ with grid discretization $dx_{\text{init}} = 2$ for initial position and $dv_{\text{init}} = 0.5$ for initial velocity. Blue curves show the typical vehicle trajectories under the proposed safe controller, with the blue dots as initial states.
  • Figure 4: Vehicle velocities of the proposed safe controller and baselines methods. Triangle indicates safely pass through the intersection. Square indicates collision with pedestrian.
  • Figure 5: Safety-efficiency trade-offs.
  • ...and 4 more figures

Theorems & Definitions (6)

  • Remark 1
  • Remark 2
  • Definition 1
  • Theorem 3
  • proof
  • Remark 4