STLGame: Signal Temporal Logic Games in Adversarial Multi-Agent Systems

We study how to synthesize a robust and safe policy for autonomous systems under signal temporal logic (STL) tasks in adversarial settings against unknown dynamic agents. To ensure the worst-case STL satisfaction, we propose STLGame, a framework that models the multi-agent system as a two-player zero-sum game, where the ego agents try to maximize the STL satisfaction and other agents minimize it. STLGame aims to find a Nash equilibrium policy profile, which is the best case in terms of robustness against unseen opponent policies, by using the fictitious self-play (FSP) framework. FSP iteratively converges to a Nash profile, even in games set in continuous state-action spaces. We propose a gradient-based method with differentiable STL formulas, which is crucial in continuous settings to approximate the best responses at each iteration of FSP. We show this key aspect experimentally by comparing with reinforcement learning-based methods to find the best response. Experiments on two standard dynamical system benchmarks, Ackermann steering vehicles and autonomous drones, demonstrate that our converged policy is almost unexploitable and robust to various unseen opponents' policies. All code and additional experimental results can be found on our project website: https://sites.google.com/view/stlgame

PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networks

Estimating ego-pose from cameras is an important problem in robotics with applications ranging from mobile robotics to augmented reality. While SOTA models are becoming increasingly accurate, they can still be unwieldy due to high computational costs. In this paper, we propose to solve the problem by using invertible neural networks (INN) to find the mapping between the latent space of images and poses for a given scene. Our model achieves similar performance to the SOTA while being faster to train and only requiring offline rendering of low-resolution synthetic data. By using normalizing flows, the proposed method also provides uncertainty estimation for the output. We also demonstrated the efficiency of this method by deploying the model on a mobile robot.

Conformal Off-Policy Prediction for Multi-Agent Systems

Off-Policy Prediction (OPP), i.e., predicting the outcomes of a target policy using only data collected under a nominal (behavioural) policy, is a paramount problem in data-driven analysis of safety-critical systems where the deployment of a new policy may be unsafe. To achieve dependable off-policy predictions, recent work on Conformal Off-Policy Prediction (COPP) leverage the conformal prediction framework to derive prediction regions with probabilistic guarantees under the target process. Existing COPP methods can account for the distribution shifts induced by policy switching, but are limited to single-agent systems and scalar outcomes (e.g., rewards). In this work, we introduce MA-COPP, the first conformal prediction method to solve OPP problems involving multi-agent systems, deriving joint prediction regions for all agents' trajectories when one or more "ego" agents change their policies. Unlike the single-agent scenario, this setting introduces higher complexity as the distribution shifts affect predictions for all agents, not just the ego agents, and the prediction task involves full multi-dimensional trajectories, not just reward values. A key contribution of MA-COPP is to avoid enumeration or exhaustive search of the output space of agent trajectories, which is instead required by existing COPP methods to construct the prediction region. We achieve this by showing that an over-approximation of the true JPR can be constructed, without enumeration, from the maximum density ratio of the JPR trajectories. We evaluate the effectiveness of MA-COPP in multi-agent systems from the PettingZoo library and the F1TENTH autonomous racing environment, achieving nominal coverage in higher dimensions and various shift settings.

Bridging the Gap between Discrete Agent Strategies in Game Theory and Continuous Motion Planning in Dynamic Environments

Generating competitive strategies and performing continuous motion planning simultaneously in an adversarial setting is a challenging problem. In addition, understanding the intent of other agents is crucial to deploying autonomous systems in adversarial multi-agent environments. Existing approaches either discretize agent action by grouping similar control inputs, sacrificing performance in motion planning, or plan in uninterpretable latent spaces, producing hard-to-understand agent behaviors. This paper proposes an agent strategy representation via Policy Characteristic Space that maps the agent policies to a pre-specified low-dimensional space. Policy Characteristic Space enables the discretization of agent policy switchings while preserving continuity in control. Also, it provides intepretability of agent policies and clear intentions of policy switchings. Then, regret-based game-theoretic approaches can be applied in the Policy Characteristic Space to obtain high performance in adversarial environments. Our proposed method is assessed by conducting experiments in an autonomous racing scenario using scaled vehicles. Statistical evidence shows that our method significantly improves the win rate of ego agent and the method also generalizes well to unseen environments.

Learning Local Control Barrier Functions for Safety Control of Hybrid Systems

Hybrid dynamical systems are ubiquitous as practical robotic applications often involve both continuous states and discrete switchings. Safety is a primary concern for hybrid robotic systems. Existing safety-critical control approaches for hybrid systems are either computationally inefficient, detrimental to system performance, or limited to small-scale systems. To amend these drawbacks, in this paper, we propose a learningenabled approach to construct local Control Barrier Functions (CBFs) to guarantee the safety of a wide class of nonlinear hybrid dynamical systems. The end result is a safe neural CBFbased switching controller. Our approach is computationally efficient, minimally invasive to any reference controller, and applicable to large-scale systems. We empirically evaluate our framework and demonstrate its efficacy and flexibility through two robotic examples including a high-dimensional autonomous racing case, against other CBF-based approaches and model predictive control.

Multi-Modal Conformal Prediction Regions by Optimizing Convex Shape Templates

Conformal prediction is a statistical tool for producing prediction regions for machine learning models that are valid with high probability. A key component of conformal prediction algorithms is a non-conformity score function that quantifies how different a model's prediction is from the unknown ground truth value. Essentially, these functions determine the shape and the size of the conformal prediction regions. However, little work has gone into finding non-conformity score functions that produce prediction regions that are multi-modal and practical, i.e., that can efficiently be used in engineering applications. We propose a method that optimizes parameterized shape template functions over calibration data, which results in non-conformity score functions that produce prediction regions with minimum volume. Our approach results in prediction regions that are multi-modal, so they can properly capture residuals of distributions that have multiple modes, and practical, so each region is convex and can be easily incorporated into downstream tasks, such as a motion planner using conformal prediction regions. Our method applies to general supervised learning tasks, while we illustrate its use in time-series prediction. We provide a toolbox and present illustrative case studies of F16 fighter jets and autonomous vehicles, showing an up to $68\%$ reduction in prediction region area.

AV4EV: Open-Source Modular Autonomous Electric Vehicle Platform to Make Mobility Research Accessible

When academic researchers develop and validate autonomous driving algorithms, there is a challenge in balancing high-performance capabilities with the cost and complexity of the vehicle platform. Much of today's research on autonomous vehicles (AV) is limited to experimentation on expensive commercial vehicles that require large teams with diverse skills to retrofit the vehicles and test them in dedicated testing facilities. Testing the limits of safety and performance on such vehicles is costly and hazardous. It is also outside the reach of most academic departments and research groups. On the other hand, scaled-down 1/10th-1/16th scale vehicle platforms are more affordable but have limited similitude in dynamics, control, and drivability. To address this issue, we present the design of a one-third-scale autonomous electric go-kart platform with open-source mechatronics design along with fully-functional autonomous driving software. The platform's multi-modal driving system is capable of manual, autonomous, and teleoperation driving modes. It also features a flexible sensing suite for development and deployment of algorithms across perception, localization, planning, and control. This development serves as a bridge between full-scale vehicles and reduced-scale cars while accelerating cost-effective algorithmic advancements in autonomous systems research. Our experimental results demonstrate the AV4EV platform's capabilities and ease-of-use for developing new AV algorithms. All materials are available at AV4EV.org to stimulate collaborative efforts within the AV and electric vehicle (EV) communities.

Safe Control Synthesis for Hybrid Systems through Local Control Barrier Functions

Control Barrier Functions (CBF) have provided a very versatile framework for the synthesis of safe control architectures for a wide class of nonlinear dynamical systems. Typically, CBF-based synthesis approaches apply to systems that exhibit nonlinear -- but smooth -- relationship in the state of the system and linear relationship in the control input. In contrast, the problem of safe control synthesis using CBF for hybrid dynamical systems, i.e., systems which have a discontinuous relationship in the system state, remains largely unexplored. In this work, we build upon the progress on CBF-based control to formulate a theory for safe control synthesis for hybrid dynamical systems. Under the assumption that local CBFs can be synthesized for each mode of operation of the hybrid system, we show how to construct CBF that can guarantee safe switching between modes. The end result is a switching CBF-based controller which provides global safety guarantees. The effectiveness of our proposed approach is demonstrated on two simulation studies.

Learning Adaptive Safety for Multi-Agent Systems

Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing promise for safety assurance but current methods make strong assumptions about other agents and often rely on manual tuning to balance safety, feasibility, and performance. In this work, we delve into the problem of adaptive safe learning for multi-agent systems with CBF. We show how emergent behavior can be profoundly influenced by the CBF configuration, highlighting the necessity for a responsive and dynamic approach to CBF design. We present ASRL, a novel adaptive safe RL framework, to fully automate the optimization of policy and CBF coefficients, to enhance safety and long-term performance through reinforcement learning. By directly interacting with the other agents, ASRL learns to cope with diverse agent behaviours and maintains the cost violations below a desired limit. We evaluate ASRL in a multi-robot system and a competitive multi-agent racing scenario, against learning-based and control-theoretic approaches. We empirically demonstrate the efficacy and flexibility of ASRL, and assess generalization and scalability to out-of-distribution scenarios. Code and supplementary material are public online.

Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications

There has been growing interest in deep reinforcement learning (DRL) algorithm design, and reward design is one key component of DRL. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due to their expressiveness and ability to define the requirements for the states and actions of the agent. However, the literature of Signal Temporal Logic (STL) in guiding multi-agent reinforcement learning (MARL) reward design remains limited. In this paper, we propose a novel STL-guided multi-agent reinforcement learning algorithm. The STL specifications are designed to include both task specifications according to the objective of each agent and safety specifications, and the robustness values of the STL specifications are leveraged to generate rewards. We validate the advantages of our method through empirical studies. The experimental results demonstrate significant performance improvements compared to MARL without STL guidance, along with a remarkable increase in the overall safety rate of the multi-agent systems.