Interaction-Dynamics-Aware Perception Zones for Obstacle Detection Safety Evaluation

Topan, Sever; Leung, Karen; Chen, Yuxiao; Pritish, Tupekar,; Szczerbicki, Edward; Nilsson, Jan; Cox, Michael; Pavone, Marco

doi:10.1109/iv51971.2022.9827409

Cited by 13 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…αi regularization (7) where )). We highlight some important considerations for this optimization problem.…”

Section: B State-dependent Control Set Learning Proceduresmentioning

confidence: 99%

“…In future work, we can consider using a monotonic neural network [31], [32]. Pairwise joint dynamics: In the case with pairwise joint dynamics, as presented in (2), there is an additional term corresponding to the contender's input (i.e., a disturbance term), and ultimately, it will show up in (7). In particular, the HOCBF constraint becomes…”

Section: B State-dependent Control Set Learning Proceduresmentioning

confidence: 99%

“…2) Safety concept analysis: We consider a HOCBF b(x) = ∆x 2 a 2 + ∆y 2 b 2 − 1, a = 5.4, b = 2.4, and consider relative dynamics between two vehicles modeled by the simple car model (11), resulting in a relative degree of two. We applied the learning procedure outlined in Section V-B; we performed a hyperparameter sweep over the following parameters defined in (7). The values are presented in Table I, and the bolded values are the hyperparameters that we found yielded the best results.…”

Section: B Highway Drivingmentioning

confidence: 99%

“…planning objective [5], or for perception safety evaluation metrics [6], [7]. Critically, different behavioral assumptions lead to different safety concepts which in turn affects realized AV safety and performance.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Leung¹,

Veer²,

Szczerbicki³

et al. 2022

Preprint

View full text Add to dashboard Cite

Evaluating the safety of an autonomous vehicle (AV) depends on the behavior of surrounding agents which can be heavily influenced by factors such as environmental context and informally-defined driving etiquette. A key challenge is in determining a minimum set of assumptions on what constitutes reasonable foreseeable behaviors of other road users for the development of AV safety models and techniques. In this paper, we propose a data-driven AV safety design methodology that first learns "reasonable" behavioral assumptions from data, and then synthesizes an AV safety concept using these learned behavioral assumptions. We borrow techniques from control theory, namely high order control barrier functions and Hamilton-Jacobi reachability, to provide inductive bias to aid interpretability, verifiability, and tractability of our approach. In our experiments, we learn an AV safety concept using demonstrations collected from a highway traffic-weaving scenario, compare our learned concept to existing baselines, and showcase its efficacy in evaluating real-world driving logs.

show abstract

“…αi regularization (7) where )). We highlight some important considerations for this optimization problem.…”

Section: B State-dependent Control Set Learning Proceduresmentioning

confidence: 99%

Section: B State-dependent Control Set Learning Proceduresmentioning

confidence: 99%

Section: B Highway Drivingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Leung¹,

Veer²,

Szczerbicki³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…{stopan, yuxiaoc, eschmerling, kaleung, jonasn, mbc, mpavone}@nvidia.com (AV), in practice perception system performance should be optimized for a more restricted, task-specific perception zone. Prior works have defined such AV perception zones on the basis of predictive assumptions on agent behavior [2], [3] or otherwise first-principles reachability analysis considering the underlying dynamics of the AV-obstacle interaction [4].…”

Section: Introductionmentioning

confidence: 99%

Refining Obstacle Perception Safety Zones via Maneuver-Based Decomposition

Topan¹,

Chen²,

Szczerbicki³

et al. 2023

2023 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

A critical task for developing safe autonomous driving stacks is to determine whether an obstacle is safetycritical, i.e., poses an imminent threat to the autonomous vehicle. Our previous work showed that Hamilton Jacobi reachability theory can be applied to compute interactiondynamics-aware perception safety zones that better inform an ego vehicle's perception module which obstacles are considered safety-critical. For completeness, these zones are typically larger than absolutely necessary, forcing the perception module to pay attention to a larger collection of objects for the sake of conservatism. As an improvement, we propose a maneuverbased decomposition of our safety zones that leverages information about the ego maneuver to reduce the zone volume. In particular, we propose a "temporal convolution" operation that produces safety zones for specific ego maneuvers, thus limiting the ego's behavior to reduce the size of the safety zones. We show with numerical experiments that maneuver-based zones are significantly smaller (up to 76% size reduction) than the baseline while maintaining completeness.

show abstract

Evaluating Object (Mis)Detection From a Safety and Reliability Perspective: Discussion and Measures

Ceccarelli

Montecchi

2023

IEEE Access

View full text Add to dashboard Cite

We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can impact the actor's safety and reliability. To quantify the impact of object (mis)detection on safety and reliability in the context of autonomous driving, we propose new object detection measures that reward the correct identification of objects that are most dangerous and most likely to affect driving decisions. To achieve this, we build an object criticality model to reward the detection of the objects based on proximity, orientation, and relative velocity with respect to the subject vehicle. Then, we apply our model on the recent autonomous driving dataset nuScenes, and we compare nine object detectors. Results show that, in several settings, object detectors that perform best according to the nuScenes ranking are not the preferable ones when the focus is shifted on safety and reliability.

show abstract

Interaction-Dynamics-Aware Perception Zones for Obstacle Detection Safety Evaluation

Abstract: To enable safe autonomous vehicle (AV) operations,

Cited by 13 publications

References 18 publications

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Refining Obstacle Perception Safety Zones via Maneuver-Based Decomposition

Evaluating Object (Mis)Detection From a Safety and Reliability Perspective: Discussion and Measures

Contact Info

Product

Resources

About