Learning from Demonstration (LfD) techniques enable robots to learn and generalize tasks from user demonstrations, eliminating the need for coding expertise among end-users. One established technique to implement LfD in robots is to encode demonstrations in a stable Dynamical System (DS). However, finding a stable dynamical system entails solving an optimization problem with bilinear matrix inequality (BMI) constraints, a non-convex problem which, depending on the number of scalar constraints and variables, demands significant computational resources and is susceptible to numerical issues such as floating-point errors. To address these challenges, we propose a novel compositional approach that enhances the applicability and scalability of learning stable DSs with BMIs.

This work presents a novel co-design strategy that integrates trajectory planning and control to handle STL-based tasks in autonomous robots. The method consists of two phases: (i) learning spatio-temporal motion primitives to encapsulate the inherent robot-specific constraints and (ii) constructing an STL-compliant motion plan from these primitives. Initially, we employ reinforcement learning to construct a library of control policies that perform trajectories described by the motion primitives. Then, we map motion primitives to spatiotemporal characteristics. Subsequently, we present a sampling-based STL-compliant motion planning strategy to meet the STL specification. The proposed model-free approach, which generates feasible STL-compliant motion plans across various environments, is validated on differential-drive and quadruped robots across various STL specifications. Demonstration videos are available at https://youtu.be/xo2cXRYdDPQ and detailed version at https://doi.org/10.48550/arXiv.2507.13225.

This study focuses on synthesizing controllers for unknown dynamics control-affine nonlinear systems, aiming to satisfy reach-avoid-stay (RAS) specifications within prescribed-time. The main objective is to derive a closed-form control law, incorporating a novel notion of spatiotemporal tubes, to guarantee that the system trajectories reach a designated target set while avoiding an unsafe set and adhering to state constraints. The efficacy of this approach is demonstrated through simulation.

Multi-robot exploration is a complex problem that involves multiple robots working in a shared unknown environment. In such scenarios, the safety of the robots is of paramount importance alongside the completion of the exploration task. In this paper, we propose a modular exploration framework that (i) identifies safe frontier targets for multiple robots while taking into account the system dynamics of each robot to ensure collision avoidance with previously unknown obstacles and (ii) ensures that the robots reach their exploration targets while avoiding any obstacles discovered and each other. We employ a scalable approach to generate symbolic controllers for the multi-robot system, utilizing distance functions. We also provide formal guarantees on the safety of the exploration targets and the completion of each exploration run, with the robots avoiding collisions with each other and the obstacles. We test our approach on simulation experiments and a real-world implementation to validate it.

Reinforcement Learning (RL) has progressed from simple control tasks to complex real-world challenges with large state spaces. While RL excels in these tasks, training time remains a limitation. Reward shaping is a popular solution, but existing methods often rely on value functions, which face scalability issues. This paper presents a novel safety-oriented reward-shaping framework inspired by barrier functions, offering simplicity and ease of implementation across various environments and tasks. To evaluate the effectiveness of the proposed reward formulations, we conduct simulation experiments on CartPole, Ant, and Humanoid environments, along with real-world deployment on the Unitree Go1 quadruped robot. Our results demonstrate that our method leads to 1.4-2.8 times faster convergence and as low as 50-60% actuation effort compared to the vanilla reward. In a sim-to-real experiment with the Go1 robot, we demonstrated better control and dynamics of the bot with our reward framework. We have open-sourced our code at https://github.com/Safe-RL-IISc/barrier_shaping.

Autonomous exploration in an unknown environment is widely studied, and many exploration strategies exist. However, in most of the works, safety is not usually given top priority. The reason behind the violation of safety by most of the exploration algorithms in real-world applications is the ignorance of some or all of the following factors (i) the mathematical model of the robot, (ii) practical constraints on states (like constrained steering angle, speed, etc.) and inputs (like actuator saturation), and (iii) hardware constraints such as sampling time, sensor noise, modelling uncertainties, etc. In this work, we propose an autonomous exploration framework for the 2-D exploration problem that considers the factors above to provide safety guarantees for the robot and the environment. The effectiveness of this method is shown in a high-fidelity simulation of different robots with onboard sensors in different simulation environments and real-world implementation.

This work studies formal verification of continuous-time continuous-space systems with unknown dynamics against safety specifications. The proposed framework is based on a data-driven construction of barrier certificates using which the safety of unknown systems is verified via a finite set of data collected from trajectories of systems with a priori guaranteed confidence. In the proposed scheme, we first cast the original safety problem as a robust convex program (RCP). Since the unknown model appears in one of the constraints of the proposed RCP, we provide the scenario convex program (SCP) corresponding to the original RCP by collecting finite numbers of data from systems' evolutions. We then establish a probabilistic closeness between the optimal value of SCP and that of RCP. Accordingly, we formally quantify the safety guarantee of unknown systems based on the number of data and the required level of safety confidence.

Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision trees are smaller and more explainable. We present dtControl, an easily extensible tool for representing memoryless controllers as decision trees. We give a comprehensive evaluation of various decision tree learning algorithms applied to 10 case studies arising out of correct-by-construction controller synthesis. These algorithms include two new techniques, one for using arbitrary linear binary classifiers in the decision tree learning, and one novel approach for determinizing controllers during the decision tree construction. In particular the latter turns out to be extremely efficient, yielding decision trees with a single-digit number of decision nodes on 5 of the case studies.

Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision tree representations are smaller and more explainable. We present dtControl, an easily extensible tool offering a wide variety of algorithms for representing memoryless controllers as decision trees. We highlight that the trees produced by dtControl are often very concise with a single-digit number of decision nodes. This demo is based on our tool paper [1].

In this paper, we provide a compositional framework for synthesizing hybrid controllers for interconnected discrete-time control systems enforcing specifications expressed by co-Büchi automata. In particular, we first decompose the given specification to simpler reachability tasks based on automata representing the complements of original co-Büchi automata. Then, we provide a systematic approach to solve those simpler reachability tasks by computing cor-responding control barrier functions. We show that such control barrier functions can be constructed compositionally by assuming some small-gain type conditions and composing so-called local control barrier functions computed for subsystems. We provide two systematic techniques to search for local control barrier functions for subsystems based on the sum-of-squares optimization program and counter-example guided inductive synthesis approach. Finally, we illustrate the effectiveness of our results through two large-scale case studies.

The article addresses the issue of reliability of complex embedded control systems in the safety-critical environment. In this article, we propose a novel approach to design controller that (i) guarantees the safety of nonlinear physical systems, (ii) enables safe system restart during runtime, and (iii) allows the use of complex, unverified controllers (e.g., neural networks) that drive the physical systems toward complex specifications. We use abstraction-based controller synthesis approach to design a formally verified controller that provides application and system-level fault tolerance along with safety guarantee. Moreover, our approach is implementable using a commercial-off-the-shelf (COTS) processing unit. To demonstrate the efficacy of our solution and to verify the safety of the system under various types of faults injected in applications and in the underlying real-time operating system (RTOS), we implemented the proposed controller for the inverted pendulum and three degrees-of-freedom (3-DOF) helicopter.

This paper proposes a new neuro-fuzzy learning machine called extreme learning adaptive neuro-fuzzy inference system (ELANFIS) which can be applied to control of nonlinear systems. The new learning machine combines the learning capabilities of neural networks and the explicit knowledge of the fuzzy systems as in the case of conventional adaptive neuro-fuzzy inference system (ANFIS). The parameters of the fuzzy layer of ELANFIS are not tuned to achieve faster learning speed without sacrificing the generalization capability. The proposed learning machine is used for inverse control and model predictive control of nonlinear systems. Simulation results show improved performance with very less computation time which is much essential for real time control.