Risk-aware Motion Planning for Autonomous Vehicles with Safety Specifications

Nyberg, Truls; Pek, Christian; Col, Laura Dal; Norén, Christoffer; Tůmová, Jana

doi:10.1109/iv48863.2021.9575928

Cited by 34 publications

(17 citation statements)

References 51 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, these works only evaluate the signal in the form of probability distributions instead of the robustness based on stochastic methods. For instance, the risk of violating safety specifications is estimated by a random variable in [23], where the gap between system dynamic models and the probability calculation is, however, not yet bridged since the latter only evaluates states. c) Nonlinear Regression: Supervised learning algorithms, e.g., regression and classification, have been used to model relationships between variables to improve prediction accuracy and computational efficiency.…”

Section: A Related Workmentioning

confidence: 99%

“…Inspired by the metrics described in [15], [23], the robustness of STL predicates should follow the subsequent properties to facilitate its application to planning and control problems: Property 1 (Soundness): Positive robustness is a necessary and sufficient condition for satisfying the predicate; likewise, a signal has negative robustness for violating the predicate.…”

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

Model Predictive Robustness of Signal Temporal Logic Predicates

Lin¹,

Li²,

Althoff³

2022

Preprint

View full text Add to dashboard Cite

The robustness of signal temporal logic not only assesses whether a signal adheres to a specification but also provides a measure of how much a formula is fulfilled or violated. The calculation of robustness is based on evaluating the robustness of underlying predicates. However, the robustness of predicates is usually defined in a model-free way, i.e., without including the system dynamics. Moreover, it is often nontrivial to define the robustness of complicated predicates precisely. To address these issues, we propose a notion of model predictive robustness, which provides a more systematic way of evaluating robustness compared to previous approaches by considering model-based predictions. In particular, we use Gaussian process regression to learn the robustness based on precomputed predictions so that robustness values can be efficiently computed online. We evaluate our approach for the use case of autonomous driving with predicates used in formalized traffic rules on a recorded dataset, which highlights the advantage of our approach compared to traditional approaches in terms of expressiveness. By incorporating our robustness definitions into a trajectory planner, autonomous vehicles obey traffic rules more robustly than human drivers in the dataset.

show abstract

Section: A Related Workmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

Model Predictive Robustness of Signal Temporal Logic Predicates

Lin¹,

Li²,

Althoff³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Risk-aware model predictive control was considered in [29,76], while [17,73] present data-driven and distributionally robust model predictive controllers. Risk-aware control barrier functions for safe control synthesis were proposed in [2], while [58] demonstrates the use of risk in sampling-based planning. We remark that we view these works to be orthogonal to our paper as we provide a data-driven framework for the risk assessment under complex temporal logic specifications, and we hope to inform future control design strategies.…”

Section: Related Workmentioning

confidence: 99%

Risk of Stochastic Systems for Temporal Logic Specifications

Lindemann¹,

Jiang²,

Matni³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fig. 1. Left: Simulation environment in the autonomous driving simulator CARLA. Middle: Double left turn on which we evaluate four trained neural network lane keeping controllers. Right: Cross-track error 𝑐 𝑒 and orientation error 𝜃 𝑒 used for risk verification of the neural network controllers.The wide availability of data coupled with the computational advances in artificial intelligence and machine learning promise to enable many future technologies such as autonomous driving. While there has been a variety of successful demonstrations of these technologies, critical system failures have repeatedly been reported. Even if rare, such system failures pose a serious barrier to adoption without a rigorous risk assessment. This paper presents a framework for the systematic and rigorous risk verification of systems. We consider a wide range of system specifications formulated in signal temporal logic (STL) and model the system as a stochastic process, permitting discrete-time and continuous-time stochastic processes. We then define the STL robustness risk as the risk of lacking robustness against failure. This definition is motivated as system failures are often caused by missing robustness to modeling errors, system disturbances, and distribution shifts in the underlying data generating process. Within the definition, we permit general classes of risk measures and focus on tail risk measures such as the value-at-risk and the conditional value-at-risk. While the STL robustness risk is in general hard to compute, we propose the approximate STL robustness risk as a more tractable notion that upper bounds the STL robustness risk. We show how the approximate STL robustness risk can accurately be estimated from system trajectory data. For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly. We illustrate our verification algorithm in the autonomous driving simulator CARLA and show how a least risky controller can be selected among four neural network lane keeping controllers for five meaningful system specifications.

show abstract

“…[50] models the Gaussian distributions of the errors in sensor measurements and object detection, but this modeling might be very conservative when the variances are high. [51], [52] estimate the severity of safety violations regarding state estimations. Risk management models are intended to analyze other models and systems and identify which subcomponents or sub-models are safe or dangerous.…”

Section: A Additional Related Workmentioning

confidence: 99%

“…Risk management models are intended to analyze other models and systems and identify which subcomponents or sub-models are safe or dangerous. This risk measurement should also be also computationally efficient [51] to give the real-time evaluations.…”

Section: A Additional Related Workmentioning

confidence: 99%

MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation

Roth¹,

Ji²,

Sriram³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present Multiple Scenario Verifiable Reinforcement Learning via Policy Extraction (MSVIPER), a new method for policy distillation to decision trees for improved robot navigation. MSVIPER learns an "expert" policy using any Reinforcement Learning (RL) technique involving learning a state-action mapping and then uses imitation learning to learn a decision-tree policy from it. We demonstrate that MSVIPER results in efficient decision trees and can accurately mimic the behavior of the expert policy. Moreover, we present efficient policy distillation and tree-modification techniques that take advantage of the decision tree structure to allow improvements to a policy without retraining. We use our approach to improve the performance of RL-based robot navigation algorithms for indoor and outdoor scenes. We demonstrate the benefits in terms of reduced freezing and oscillation behaviors (by up to 95% reduction) for mobile robots navigating among dynamic obstacles and reduced vibrations and oscillation (by up to 17%) for outdoor robot navigation on complex, uneven terrains.

show abstract

Risk-aware Motion Planning for Autonomous Vehicles with Safety Specifications

Cited by 34 publications

References 51 publications

Model Predictive Robustness of Signal Temporal Logic Predicates

Model Predictive Robustness of Signal Temporal Logic Predicates

Risk of Stochastic Systems for Temporal Logic Specifications

MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation

Contact Info

Product

Resources

About