An NCAP-like Safety Indicator for Self-Driving Cars
- URL: http://arxiv.org/abs/2104.00859v1
- Date: Fri, 2 Apr 2021 02:39:53 GMT
- Title: An NCAP-like Safety Indicator for Self-Driving Cars
- Authors: Jimy Cai Huang and Hanna Kurniawati
- Abstract summary: This paper proposes a mechanism to assess the safety of autonomous cars.
It assesses the car's safety in scenarios where the car must avoid collision with an adversary.
The safety measure, called Safe-Kamikaze Distance, computes the average similarity between sets of safe adversary's trajectories and kamikaze trajectories close to the safe trajectories.
- Score: 2.741266294612776
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper proposes a mechanism to assess the safety of autonomous cars. It
assesses the car's safety in scenarios where the car must avoid collision with
an adversary. Core to this mechanism is a safety measure, called Safe-Kamikaze
Distance (SKD), which computes the average similarity between sets of safe
adversary's trajectories and kamikaze trajectories close to the safe
trajectories. The kamikaze trajectories are generated based on planning under
uncertainty techniques, namely the Partially Observable Markov Decision
Processes, to account for the partially observed car policy from the point of
view of the adversary. We found that SKD is inversely proportional to the upper
bound on the probability that a small deformation changes a collision-free
trajectory of the adversary into a colliding one. We perform systematic tests
on a scenario where the adversary is a pedestrian crossing a single-lane road
in front of the car being assessed --which is, one of the scenarios in the
Euro-NCAP's Vulnerable Road User (VRU) tests on Autonomous Emergency Braking.
Simulation results on assessing cars with basic controllers and a test on a
Machine-Learning controller using a high-fidelity simulator indicates promising
results for SKD to measure the safety of autonomous cars. Moreover, the time
taken for each simulation test is under 11 seconds, enabling a sufficient
statistics to compute SKD from simulation to be generated on a quad-core
desktop in less than 25 minutes.
Related papers
- Rigorous Simulation-based Testing for Autonomous Driving Systems -- Targeting the Achilles' Heel of Four Open Autopilots [6.229766691427486]
We propose a rigorous test method based on breaking down scenarios into simple ones.
We generate test cases for critical configurations that place the vehicle under test in critical situations.
Test cases reveal major defects in Apollo, Autoware, and the Carla and LGSVL autopilots.
arXiv Detail & Related papers (2024-05-27T08:06:21Z) - PAFOT: A Position-Based Approach for Finding Optimal Tests of Autonomous Vehicles [4.243926243206826]
This paper proposes PAFOT, a position-based approach testing framework.
PAFOT generates adversarial driving scenarios to expose safety violations of Automated Driving Systems.
Experiments show PAFOT can effectively generate safety-critical scenarios to crash ADSs and is able to find collisions in a short simulation time.
arXiv Detail & Related papers (2024-05-06T10:04:40Z) - CAT: Closed-loop Adversarial Training for Safe End-to-End Driving [54.60865656161679]
Adversarial Training (CAT) is a framework for safe end-to-end driving in autonomous vehicles.
Cat aims to continuously improve the safety of driving agents by training the agent on safety-critical scenarios.
Cat can effectively generate adversarial scenarios countering the agent being trained.
arXiv Detail & Related papers (2023-10-19T02:49:31Z) - DeepAccident: A Motion and Accident Prediction Benchmark for V2X
Autonomous Driving [76.29141888408265]
We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving.
The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
arXiv Detail & Related papers (2023-04-03T17:37:00Z) - Evaluation of Pedestrian Safety in a High-Fidelity Simulation Environment Framework [21.456269382916062]
This paper proposes a pedestrian safety evaluation method for autonomous driving.
We construct a high-fidelity simulation framework embedded with pedestrian safety-critical characteristics.
The proposed simulation method and framework can be used to access different autonomous driving algorithms.
arXiv Detail & Related papers (2022-10-17T03:53:50Z) - A Certifiable Security Patch for Object Tracking in Self-Driving Systems
via Historical Deviation Modeling [22.753164675538457]
We present the first systematic research on the security of object tracking in self-driving cars.
We prove the mainstream multi-object tracker (MOT) based on Kalman Filter (KF) is unsafe even with an enabled multi-sensor fusion mechanism.
We propose a simple yet effective security patch for KF-based MOT, the core of which is an adaptive strategy to balance the focus of KF on observations and predictions.
arXiv Detail & Related papers (2022-07-18T12:30:24Z) - Prediction-Based Reachability Analysis for Collision Risk Assessment on
Highways [18.18842948832662]
This paper introduces a prediction-based collision risk assessment approach on highways.
We develop an acceleration prediction model, which provides multi-modal probabilistic acceleration distributions to propagate vehicle states.
The proposed collision detection approach is agile and effective to identify the collision in cut-in crash events.
arXiv Detail & Related papers (2022-05-03T07:58:02Z) - Differentiable Control Barrier Functions for Vision-based End-to-End
Autonomous Driving [100.57791628642624]
We introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving.
We design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent.
arXiv Detail & Related papers (2022-03-04T16:14:33Z) - Safety-aware Motion Prediction with Unseen Vehicles for Autonomous
Driving [104.32241082170044]
We study a new task, safety-aware motion prediction with unseen vehicles for autonomous driving.
Unlike the existing trajectory prediction task for seen vehicles, we aim at predicting an occupancy map.
Our approach is the first one that can predict the existence of unseen vehicles in most cases.
arXiv Detail & Related papers (2021-09-03T13:33:33Z) - Generating and Characterizing Scenarios for Safety Testing of Autonomous
Vehicles [86.9067793493874]
We propose efficient mechanisms to characterize and generate testing scenarios using a state-of-the-art driving simulator.
We use our method to characterize real driving data from the Next Generation Simulation (NGSIM) project.
We rank the scenarios by defining metrics based on the complexity of avoiding accidents and provide insights into how the AV could have minimized the probability of incurring an accident.
arXiv Detail & Related papers (2021-03-12T17:00:23Z) - Can Autonomous Vehicles Identify, Recover From, and Adapt to
Distribution Shifts? [104.04999499189402]
Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment.
We propose an uncertainty-aware planning method, called emphrobust imitative planning (RIP)
Our method can detect and recover from some distribution shifts, reducing the overconfident and catastrophic extrapolations in OOD scenes.
We introduce an autonomous car novel-scene benchmark, textttCARNOVEL, to evaluate the robustness of driving agents to a suite of tasks with distribution shifts.
arXiv Detail & Related papers (2020-06-26T11:07:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.