Failing with Grace: Learning Neural Network Controllers that are Boundedly Unsafe
In this work, we consider the problem of learning a feed-forward neural network controller to safely steer an arbitrarily shaped planar robot in a compact and obstacle-occluded workspace. Unlike existing methods that depend strongly on the density of data points close to the boundary of the safe state space to train neural network controllers with closed-loop safety guarantees, here we propose an alternative approach that lifts such strong assumptions on the data that are hard to satisfy in practice and instead allows for graceful safety violations, i.e., of a bounded magnitude that can be spatially controlled. To do so, we employ reachability analysis techniques to encapsulate safety constraints in the training process. Specifically, to obtain a computationally efficient over-approximation of the forward reachable set of the closed-loop system, we partition the robot's state space into cells and adaptively subdivide the cells that contain states which may escape the safe set under the trained control law. Then, using the overlap between each cell's forward reachable set and the set of infeasible robot configurations as a measure for safety violations, we introduce appropriate terms into the loss function that penalize this overlap in the training process. As a result, our method can learn a safe vector field for the closed-loop system and, at the same time, provide worst-case bounds on safety violation over the whole configuration space, defined by the overlap between the over-approximation of the forward reachable set of the closed-loop system and the set of unsafe states. Moreover, it can control the tradeoff between computational complexity and tightness of these bounds. Our proposed method is supported by both theoretical results and simulation studies.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Leveraging Gated Recurrent Units for Iterative Online Precise Attitude Control for Geodetic Missions
In this paper, we consider the problem of precise attitude control for geodetic missions, such as the GRACE Follow-on (GRACE-FO) mission. Traditional and well-established control methods, such as Proportional-Integral-De…
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Adversarial threats against LLMs are escalating faster than current defenses can adapt. We expose a critical geometric blind spot in alignment: adversarial prompts exploit latent camouflage, embedding perilously close to…
Adversarial AttackSafety AlignmentInternal State-Based Policy Gradient Methods for Partially Observable Markov Potential Games
This letter studies multi-agent reinforcement learning in partially observable Markov potential games. Solving this problem is challenging due to partial observability, decentralized information, and the curse of dimensi…
Multi-agent Reinforcement LearningLearning and Adapting Agile Locomotion Skills by Transferring Experience
Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running. However, designing robust controllers for highly agile dynamic motions remains a substant…
Reinforcement Learning (RL)Safety-Enhanced Self-Learning for Optimal Power Converter Control
Data-driven learning-based control methods such as reinforcement learning (RL) have become increasingly popular with recent proliferation of the machine learning paradigm. These methods address the parameter sensitivenes…
Model Predictive ControlReinforcement Learning (RL)Self-Learning