SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation

• URL: http://arxiv.org/abs/2409.10320v2
• Date: Mon, 17 Feb 2025 23:48:52 GMT
• Title: SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation
• Authors: Benjamin Stoler, Ingrid Navarro, Jonathan Francis, Jean Oh,
• Abstract summary: We propose SEAL, a scenario approach which leverages learned objective functions and adversarial, human-like skills. SEAL-perturbed scenarios are more realistic than SOTA baselines, leading to improved ego task success across real-world, in-distribution, and out-of-distribution scenarios.
• Score: 13.008446845017454
• License:
• Abstract: Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies through closed-loop training. However, existing approaches for scenario generation rely on simplistic objectives, resulting in overly-aggressive or non-reactive adversarial behaviors. To generate diverse adversarial yet realistic scenarios, we propose SEAL, a scenario perturbation approach which leverages learned objective functions and adversarial, human-like skills. SEAL-perturbed scenarios are more realistic than SOTA baselines, leading to improved ego task success across real-world, in-distribution, and out-of-distribution scenarios, of more than 20%. To facilitate future research, we release our code and tools: https://github.com/cmubig/SEAL

Related papers

• LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models [39.139025989575686]
  AClosed-loop adversarial scenario generation framework leveraging large language models (LLMs) adversarial scenario generation methods are developed, in which behaviors of traffic participants are manipulated to induce safety-critical events. LLMs-attacker can create more dangerous scenarios than other methods, and the ADS trained with it achieves a collision rate half that of training with normal scenarios.
  arXiv  Detail & Related papers  (2025-01-27T08:18:52Z)
• Multi-UAV Pursuit-Evasion with Online Planning in Unknown Environments by Deep Reinforcement Learning [16.761470423715338]
  Multi-UAV pursuit-evasion poses a key challenge for UAV swarm intelligence. We introduce an evader prediction-enhanced network to tackle partial observability in cooperative strategy learning. We derive a feasible policy via a two-stage reward refinement and deploy the policy on real quadrotors in a zero-shot manner.
  arXiv  Detail & Related papers  (2024-09-24T08:40:04Z)
• ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable [88.08120417169971]
  Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner.
  arXiv  Detail & Related papers  (2024-09-12T08:26:33Z)
• SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning [26.554847852013737]
  SoNIC is the first algorithm that integrates adaptive conformal inference and constrained reinforcement learning. Our method achieves a success rate of 96.93%, which is 11.67% higher than the previous state-of-the-art RL method. Our experiments demonstrate that the system can generate robust and socially polite decision-making when interacting with both sparse and dense crowds.
  arXiv  Detail & Related papers  (2024-07-24T17:57:21Z)
• SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation [54.97931304488993]
  Self-improving robots that interact and improve with experience are key to the real-world deployment of robotic systems. We propose an online learning method, SELFI, that leverages online robot experience to rapidly fine-tune pre-trained control policies. We report improvements in terms of collision avoidance, as well as more socially compliant behavior, measured by a human user study.
  arXiv  Detail & Related papers  (2024-03-01T21:27:03Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Learning Vision-based Pursuit-Evasion Robot Policies [54.52536214251999]
  We develop a fully-observable robot policy that generates supervision for a partially-observable one. We deploy our policy on a physical quadruped robot with an RGB-D camera on pursuit-evasion interactions in the wild.
  arXiv  Detail & Related papers  (2023-08-30T17:59:05Z)
• Learning for Visual Navigation by Imagining the Success [66.99810227193196]
  We propose to learn to imagine a latent representation of the successful (sub-)goal state. ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success. We develop an efficient learning algorithm to train ForeSIT in an on-policy manner and integrate it into our RL objective.
  arXiv  Detail & Related papers  (2021-02-28T10:25:46Z)
• Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework [30.58186749790728]
  We propose a theoretically-justified approach to maintaining safety in the presence of dynamics uncertainty. Our framework guarantees the high-probability satisfaction of all constraints at all times jointly. This theoretical analysis also motivates two regularizers of last-layer meta-learning models that improve online adaptation capabilities.
  arXiv  Detail & Related papers  (2020-08-26T17:39:58Z)
• Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings [129.80279257258098]
  Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous. We propose a "safety-critical adaptation" task setting: an agent first trains in non-safety-critical "source" environments. We propose a solution approach, CARL, that builds on the intuition that prior experience in diverse environments equips an agent to estimate risk.
  arXiv  Detail & Related papers  (2020-08-15T01:40:59Z)

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.