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.

The proliferation of unmanned aerial vehicles (UAVs) in controlled airspace presents significant risks, including potential collisions, disruptions to air traffic, and security threats. Ensuring the safe and efficient operation of airspace, particularly in urban environments and near critical infrastructure, necessitates effective methods to intercept unauthorized or non-cooperative UAVs. This work addresses the critical need for robust, adaptive systems capable of managing such threats through the use of Reinforcement Learning (RL). We present a novel approach utilizing RL to train fixed-wing UAV pursuer agents for intercepting dynamic evader targets. Our methodology explores both model-based and model-free RL algorithms, specifically DreamerV3, Truncated Quantile Critics (TQC), and Soft Actor-Critic (SAC). The training and evaluation of these algorithms were conducted under diverse scenarios, including unseen evasion strategies and environmental perturbations. Our approach leverages high-fidelity flight dynamics simulations to create realistic training environments. This research underscores the importance of developing intelligent, adaptive control systems for UAV interception, significantly contributing to the advancement of secure and efficient airspace management. It demonstrates the potential of RL to train systems capable of autonomously achieving these critical tasks.

This work presents HiLMa-Res, a hierarchical framework leveraging reinforcement learning to tackle manipulation tasks while performing continuous locomotion using quadrupedal robots. Unlike most previous efforts that focus on solving a specific task, HiLMa-Res is designed to be general for various loco-manipulation tasks that require quadrupedal robots to maintain sustained mobility. The novel design of this framework tackles the challenges of integrating continuous locomotion control and manipulation using legs. It develops an operational space locomotion controller that can track arbitrary robot end-effector (toe) trajectories while walking at different velocities. This controller is designed to be general to different downstream tasks, and therefore, can be utilized in high-level manipulation planning policy to address specific tasks. To demonstrate the versatility of this framework, we utilize HiLMa-Res to tackle several challenging loco-manipulation tasks using a quadrupedal robot in the real world. These tasks span from leveraging state-based policy to vision-based policy, from training purely from the simulation data to learning from real-world data. In these tasks, HiLMa-Res shows better performance than other methods.

This study examines the problem of hopping robot navigation planning to achieve simultaneous goal-directed and environment exploration tasks. We consider a scenario in which the robot has mandatory goal-directed tasks defined using Linear Temporal Logic (LTL) specifications as well as optional exploration tasks represented using a reward function. Additionally, there exists uncertainty in the robot dynamics which results in motion perturbation. We first propose an abstraction of 3D hopping robot dynamics which enables high-level planning and a neural-network-based optimization for low-level control. We then introduce a Multi-task Product IMDP (MT-PIMDP) model of the system and tasks. We propose a unified control policy synthesis algorithm which enables both task-directed goal-reaching behaviors as well as task-agnostic exploration to learn perturbations and reward. We provide a formal proof of the trade-off induced by prioritizing either LTL or RL actions. We demonstrate our methods with simulation case studies in a 2D world navigation environment.

Periodic activation functions, often referred to as learned Fourier features have been widely demonstrated to improve sample efficiency and stability in a variety of deep RL algorithms. Potentially incompatible hypotheses have been made about the source of these improvements. One is that periodic activations learn low frequency representations and as a result avoid overfitting to bootstrapped targets. Another is that periodic activations learn high frequency representations that are more expressive, allowing networks to quickly fit complex value functions. We analyse these claims empirically, finding that periodic representations consistently converge to high frequencies regardless of their initialisation frequency. We also find that while periodic activation functions improve sample efficiency, they exhibit worse generalization on states with added observation noise -- especially when compared to otherwise equivalent networks with ReLU activation functions. Finally, we show that weight decay regularization is able to partially offset the overfitting of periodic activation functions, delivering value functions that learn quickly while also generalizing.

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to--or knowledge of--an underlying, unobservable state space. Our metric, the $\lambda$-discrepancy, is the difference between two distinct temporal difference (TD) value estimates, each computed using TD($\lambda$) with a different value of $\lambda$. Since TD($\lambda$=0) makes an implicit Markov assumption and TD($\lambda$=1) does not, a discrepancy between these estimates is a potential indicator of a non-Markovian state representation. Indeed, we prove that the $\lambda$-discrepancy is exactly zero for all Markov decision processes and almost always non-zero for a broad class of partially observable environments. We also demonstrate empirically that, once detected, minimizing the $\lambda$-discrepancy can help with learning a memory function to mitigate the corresponding partial observability. We then train a reinforcement learning agent that simultaneously constructs two recurrent value networks with different $\lambda$ parameters and minimizes the difference between them as an auxiliary loss. The approach scales to challenging partially observable domains, where the resulting agent frequently performs significantly better (and never performs worse) than a baseline recurrent agent with only a single value network.

Continuum and soft robots can positively impact diverse sectors, from biomedical applications to marine and space exploration, thanks to their potential to adaptively interact with unstructured environments. However, the complex mechanics exhibited by these robots pose diverse challenges in modeling and control. Reduced order continuum mechanical models based on rod theories have emerged as a promising framework, striking a balance between accurately capturing deformations of slender bodies and computational efficiency. This review paper explores rod-based models and control strategies for continuum and soft robots. In particular, it summarizes the mathematical background underlying the four main rod theories applied in soft robotics. Then, it categorizes the literature on rod models applied to continuum and soft robots based on deformation classes, actuation technology, or robot type. Finally, it reviews recent model-based and learning-based control strategies leveraging rod models. The comprehensive review includes a critical discussion of the trends, advantages, limits, and possible future developments of rod models. This paper could guide researchers intending to simulate and control new soft robots and provide feedback to the design and manufacturing community.

Controlling the evolution of complex physical systems is a fundamental task across science and engineering. Classical techniques suffer from limited applicability or huge computational costs. On the other hand, recent deep learning and reinforcement learning-based approaches often struggle to optimize long-term control sequences under the constraints of system dynamics. In this work, we introduce Diffusion Physical systems Control (DiffPhyCon), a new class of method to address the physical systems control problem. DiffPhyCon excels by simultaneously minimizing both the learned generative energy function and the predefined control objectives across the entire trajectory and control sequence. Thus, it can explore globally and identify near-optimal control sequences. Moreover, we enhance DiffPhyCon with prior reweighting, enabling the discovery of control sequences that significantly deviate from the training distribution. We test our method in 1D Burgers' equation and 2D jellyfish movement control in a fluid environment. Our method outperforms widely applied classical approaches and state-of-the-art deep learning and reinforcement learning methods. Notably, DiffPhyCon unveils an intriguing fast-close-slow-open pattern observed in the jellyfish, aligning with established findings in the field of fluid dynamics.

A key challenge in lifelong reinforcement learning (RL) is the loss of plasticity, where previous learning progress hinders an agent's adaptation to new tasks. While regularization and resetting can help, they require precise hyperparameter selection at the outset and environment-dependent adjustments. Building on the principled theory of online convex optimization, we present a parameter-free optimizer for lifelong RL, called TRAC, which requires no tuning or prior knowledge about the distribution shifts. Extensive experiments on Procgen, Atari, and Gym Control environments show that TRAC works surprisingly well-mitigating loss of plasticity and rapidly adapting to challenging distribution shifts-despite the underlying optimization problem being nonconvex and nonstationary.

Urban congestion remains a critical challenge, with traffic signal control (TSC) emerging as a potent solution. TSC is often modeled as a Markov Decision Process problem and then solved using reinforcement learning (RL), which has proven effective. However, the existing RL-based TSC system often overlooks imperfect observations caused by degraded communication, such as packet loss, delays, and noise, as well as rare real-life events not included in the reward function, such as unconsidered emergency vehicles. To address these limitations, we introduce a novel integration framework that combines a large language model (LLM) with RL. This framework is designed to manage overlooked elements in the reward function and gaps in state information, thereby enhancing the policies of RL agents. In our approach, RL initially makes decisions based on observed data. Subsequently, LLMs evaluate these decisions to verify their reasonableness. If a decision is found to be unreasonable, it is adjusted accordingly. Additionally, this integration approach can be seamlessly integrated with existing RL-based TSC systems without necessitating modifications. Extensive testing confirms that our approach reduces the average waiting time by $17.5\%$ in degraded communication conditions as compared to traditional RL methods, underscoring its potential to advance practical RL applications in intelligent transportation systems. The related code can be found at \url{https://github.com/Traffic-Alpha/iLLM-TSC}.