相关论文: Runtime Safety Assurance Using Reinforcement Learn…

A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…

The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety of the agent during…

Run Time Assurance (RTA) Systems are online verification mechanisms that filter an unverified primary controller output to ensure system safety. The primary control may come from a human operator, an advanced control approach, or an…

As autonomous systems become more prevalent in the real world, it is critical to ensure they operate safely. One approach is the use of Run Time Assurance (RTA), which is a real-time safety assurance technique that monitors a primary…

On-orbit spacecraft inspection is an important capability for enabling servicing and manufacturing missions and extending the life of spacecraft. However, as space operations become increasingly more common and complex, autonomous control…

Runtime assurance (RTA) addresses the problem of keeping an autonomous system safe while using an untrusted (or experimental) controller. This can be done via logic that explicitly switches between the untrusted controller and a safety…

As the number of spacecraft on orbit continues to grow, it is challenging for human operators to constantly monitor and plan for all missions. Autonomous control methods such as reinforcement learning (RL) have the power to solve complex…

Model-based reinforcement learning (RL) has emerged as a promising tool for developing controllers for real world systems (e.g., robotics, autonomous driving, etc.). However, real systems often have constraints imposed on their state space…

This research considers the problem of identifying safety constraints and developing Run Time Assurance (RTA) for Deep Reinforcement Learning (RL) Tactical Autopilots that use neural network control systems (NNCS). This research studies a…

This paper presents a risk-aware safe reinforcement learning (RL) control design for stochastic discrete-time linear systems. Rather than using a safety certifier to myopically intervene with the RL controller, a risk-informed safe…

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Run Time Assurance (RTA) systems are online safety verification techniques that filter the output of a primary controller to assure safety. RTA approaches are used in safety-critical control to intervene when a performance-driven primary…

Cyber-physical systems (CPSes), such as autonomous vehicles, use sophisticated components like ML-based controllers. It is difficult to provide evidence about the safe functioning of such components. To overcome this problem, Runtime…

Vanilla Reinforcement Learning (RL) can efficiently solve complex tasks but does not provide any guarantees on system behavior. To bridge this gap, we propose a three-step safe RL procedure for continuous action spaces that provides…

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory.…

While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles,…

Recent advances in artificial intelligence and machine learning may soon yield paradigm-shifting benefits for aerospace systems. However, complexity and possible continued on-line learning makes neural network control systems (NNCS)…

As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional…