Kerianne L. Hobbs

Nathaniel Hamilton, Kyle Dunlap, Taylor T Johnson et al.

Reinforcement Learning (RL) has become an increasingly important research area as the success of machine learning algorithms and methods grows. To combat the safety concerns surrounding the freedom given to RL agents while training, there has been an increase in work concerning Safe Reinforcement Learning (SRL). However, these new and safe methods have been held to less scrutiny than their unsafe counterparts. For instance, comparisons among safe methods often lack fair evaluation across similar initial condition bounds and hyperparameter settings, use poor evaluation metrics, and cherry-pick the best training runs rather than averaging over multiple random seeds. In this work, we conduct an ablation study using evaluation best practices to investigate the impact of run time assurance (RTA), which monitors the system state and intervenes to assure safety, on effective learning. By studying multiple RTA approaches in both on-policy and off-policy RL algorithms, we seek to understand which RTA methods are most effective, whether the agents become dependent on the RTA, and the importance of reward shaping versus safe exploration in RL agent training. Our conclusions shed light on the most promising directions of SRL, and our evaluation methodology lays the groundwork for creating better comparisons in future SRL work.

Udayan Mandal, Guy Amir, Haoze Wu et al.

In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospace systems and safety-critical domains, in which a single mistake can have dire consequences. In this paper, we present novel advancements in both the training and verification of DRL controllers, which can help ensure their safe behavior. We showcase a design-for-verification approach utilizing k-induction and demonstrate its use in verifying liveness properties. In addition, we also give a brief overview of neural Lyapunov Barrier certificates and summarize their capabilities on a case study. Finally, we describe several other novel reachability-based approaches which, despite failing to provide guarantees of interest, could be effective for verification of other DRL systems, and could be of further interest to the community.

Kerianne L. Hobbs, Bernard Li

Designing a safe, trusted, and ethical AI may be practically impossible; however, designing AI with safe, trusted, and ethical use in mind is possible and necessary in safety and mission-critical domains like aerospace. Safe, trusted, and ethical use of AI are often used interchangeably; however, a system can be safely used but not trusted or ethical, have a trusted use that is not safe or ethical, and have an ethical use that is not safe or trusted. This manuscript serves as a primer to illuminate the nuanced differences between these concepts, with a specific focus on applications of Human-AI teaming in aerospace system control, where humans may be in, on, or out-of-the-loop of decision-making.

Kristina Miller, Christopher K. Zeitler, William Shen et al.

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 that assures safety by switching to the safety controller as needed, while maximizing some performance criteria, such as the utilization of the untrusted controller. Existing RTA design strategies are well-known to be overly conservative and, in principle, can lead to safety violations. In this paper, we formulate the optimal RTA design problem and present a new approach for solving it. Our approach relies on reward shaping and reinforcement learning. It can guarantee safety and leverage machine learning technologies for scalability. We have implemented this algorithm and present experimental results comparing our approach with state-of-the-art reachability and simulation-based RTA approaches in a number of scenarios using aircraft models in 3D space with complex safety requirements. Our approach can guarantee safety while increasing utilization of the experimental controller over existing approaches.

Nathaniel Hamilton, Kyle Dunlap, Kerianne L. Hobbs

For many space applications, traditional control methods are often used during operation. However, as the number of space assets continues to grow, autonomous operation can enable rapid development of control methods for different space related tasks. One method of developing autonomous control is Reinforcement Learning (RL), which has become increasingly popular after demonstrating promising performance and success across many complex tasks. While it is common for RL agents to learn bounded continuous control values, this may not be realistic or practical for many space tasks that traditionally prefer an on/off approach for control. This paper analyzes using discrete action spaces, where the agent must choose from a predefined list of actions. The experiments explore how the number of choices provided to the agents affects their measured performance during and after training. This analysis is conducted for an inspection task, where the agent must circumnavigate an object to inspect points on its surface, and a docking task, where the agent must move into proximity of another spacecraft and "dock" with a low relative speed. A common objective of both tasks, and most space tasks in general, is to minimize fuel usage, which motivates the agent to regularly choose an action that uses no fuel. Our results show that a limited number of discrete choices leads to optimal performance for the inspection task, while continuous control leads to optimal performance for the docking task.

Nathaniel Hamilton, Kyle Dunlap, Kerianne L Hobbs

Recent research using Reinforcement Learning (RL) to learn autonomous control for spacecraft operations has shown great success. However, a recent study showed their performance could be improved by changing the action space, i.e. control outputs, used in the learning environment. This has opened the door for finding more improvements through further changes to the environment. The work in this paper focuses on how changes to the environment's observation space can impact the training and performance of RL agents learning the spacecraft inspection task. The studies are split into two groups. The first looks at the impact of sensors that were designed to help agents learn the task. The second looks at the impact of reference frames, reorienting the agent to see the world from a different perspective. The results show the sensors are not necessary, but most of them help agents learn more optimal behavior, and that the reference frame does not have a large impact, but is best kept consistent.