SAFEUP

People

Xinwei Wang - Postdoctoral researcher

Prof. Meng Wang

Prof. Javier Alonso-Mora

Funding

This work was supported in part by the SAFE-UP Project through the European Union’s Horizon 2020 Research and Innovation Program under Grant 861570

About the Project

Autonomous vehicles are expected to improve road safety and significantly benefit future mobility. Highways are generally structured environments which are designed for vehicles to consistently drive at a high speed. Most autonomous vehicles(AVs) are firstly developed for highway driving and is usually considered to be the first test bench for a transition from human-driven vehicles to high-level AVs. This however makes it essential to address driving safety and develop risk metrics which can be used to assess collision detection systems for these vehicles. This project proposes novel collision detection methods and a risk metric for highway driving applications.

One key component in safety analysis is identifying a metric capable of quantifying the risk level. Surrogate measures of safety (SMoS) are typically used as they focus on temporal events prior to the crash which can be useful in predicting their occurence. This project focuses on the development of a new SMoS termed as prediction-based probabilistic driving risk field(P-PDRF) which makes use of multi-modal trajectory predictions within a time horizon. This mainly refers to different lane change maneuvers and calculates the sum of weighted risks over each maneuver in a set of maneuver possibilities. This metric is capable of real-time applicaions and is able to classify between a crash and non-crash events. A trajectory dataset is used to validate the benefit of using this metric.

Another contribution of this project was the development of a collision detection method based on a forward reachable set (FRS). This is done using a reachability analysis (RA) which computes a complete set of states that the agent can reach based on initial conditions. This set is then compared with that of the other road users to ensure that there is no overlap. This is done using a neural-network based prediction model that can be trained to minimize vehicle position errors.

Project Demonstrations

Funding & Partners

This work was supported in part by the SAFE-UP Project through the European Union’s Horizon 2020 Research and Innovation Program under Grant 861570.

Reachability-based confidence-aware probabilistic collision detection in highway driving
Xinwei Wang, Zirui Li, Javier Alonso-Mora, Meng Wang. In S.I. Safety for Intelligent and Connected Vehicles, Engineering, 2024.

abstract pdf

Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles. Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions. However, they suffer from over-conservatism, potentially resulting in false–positive risk events in complicated real-world applications. In this paper, we combine two reachability analysis techniques, a backward reachable set (BRS) and a stochastic forward reachable set (FRS), and propose an integrated probabilistic collision–detection framework for highway driving. Within this framework, we can first use a BRS to formally check whether a two-vehicle interaction is safe; otherwise, a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step. Thus, the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events. To construct the stochastic FRS, we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy. Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data. The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios. The proposed risk assessment framework is promising for real-world applications.

Probabilistic Risk Assessment for Chance-Constrained Collision Avoidance in Uncertain Dynamic Environments
Khaled A. Mustafa, Oscar de Groot, Xinwei Wang, Jens Kober, Javier Alonso-Mora. In IEEE International Conference on Robotics and Automation (ICRA), 2023.

abstract pdf

Balancing safety and efficiency when planning in crowded scenarios with uncertain dynamics is challenging where it is imperative to accomplish the robot’s mission without incurring any safety violations. Typically, chance constraints are incorporated into the planning problem to provide probabilistic safety guarantees by imposing an upper bound on the collision probability of the planned trajectory. Yet, this results in overly conservative behavior on the grounds that the gap between the obtained risk and the specified upper limit is not explicitly restricted. To address this issue, we propose a real-time capable approach to quantify the risk associated with planned trajec- tories obtained from multiple probabilistic planners, running in parallel, with different upper bounds of the acceptable risk level. Based on the evaluated risk, the least conservative plan is selected provided that its associated risk is below a specified threshold. In such a way, the proposed approach provides probabilistic safety guarantees by attaining a closer bound to the specified risk, while being applicable to generic uncertainties of moving obstacles. We demonstrate the efficiency of our proposed approach, by improving the performance of a state- of-the-art probabilistic planner, in simulations and experiments using a mobile robot in an environment shared with humans.

Probabilistic risk metric for highway driving leveraging multi-modal trajectory prediction
X. Wang, J. Alonso-Mora, M. Wang. In , IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022.

abstract publisher pdf

Road traffic safety has attracted increasing research attention, in particular in the current transition from human-driven vehicles to autonomous vehicles. Surrogate measures of safety are widely used to assess traffic safety but they typically ignore motion uncertainties and are inflexible in dealing with two-dimensional motion. Meanwhile, learning-based lane-change and trajectory prediction models have shown potential to provide accurate prediction results. We therefore propose a prediction-based driving risk metric for two-dimensional motion on multi-lane highways, expressed by the maximum risk value over different time instants within a prediction horizon. At each time instant, the risk of the vehicle is estimated as the sum of weighted risks over each mode in a finite set of lane-change maneuver possibilities. Under each maneuver mode, the risk is calculated as the product of three factors: lane-change maneuver mode probability, collision probability and expected crash severity. The three factors are estimated leveraging two-stage multi-modal trajectory predictions for surrounding vehicles: first a lane-change intention prediction module is invoked to provide lane-change maneuver mode possibilities, and then the mode possibilities are used as partial input for a multi-modal trajectory prediction module. Working with the empirical trajectory dataset highD and simulated highway scenarios, the proposed two-stage model achieves superior performance compared to a state-of-the-art prediction model. The proposed risk metric is computationally efficient for real-time applications, and effective to identify potential crashes earlier thanks to the employed prediction model.

Reachability-based confidence-aware probabilistic collision detection in highway driving
X. Wang, Z. Li, J. Alonso-Mora, M. Wang. In 4th Symposium on Management of Future motorway and urban Traffic Systems (MFTS), Dresden, Germany, 2022.

abstract pdf slides

Links: [pdf], [slides],

Prediction-Based Reachability Analysis for Collision Risk Assessment on Highways
X. Wang, Z. Li, J. Alonso-Mora, M. Wang. In IEEE Intelligent Vehicles Symposium (IV), 2022.

abstract arxiv pdf

Real-time safety systems are crucial components of intelligent vehicles. This paper introduces a prediction-based collision risk assessment approach on highways. Given a point mass vehicle dynamics system, a stochastic forward reachable set considering two-dimensional motion with vehicle state probability distributions is firstly established. We then develop an acceleration prediction model, which provides multi-modal probabilistic acceleration distributions to propagate vehicle states. The collision probability is calculated by summing up the probabilities of the states where two vehicles spatially overlap. Simulation results show that the prediction model has superior performance in terms of vehicle motion position errors, and the proposed collision detection approach is agile and effective to identify the collision in cut-in crash events.