English
Related papers

Related papers: Probabilistic Safety Constraints for Learned High …

200 papers

Control barrier functions have shown great success in addressing control problems with safety guarantees. These methods usually find the next safe control input by solving an online quadratic programming problem. However, model uncertainty…

Systems and Control · Electrical Eng. & Systems 2020-11-24 Chuanzheng Wang , Yinan Li , Yiming Meng , Stephen L. Smith , Jun Liu

We propose a learning-based robust predictive control algorithm that compensates for significant uncertainty in the dynamics for a class of discrete-time systems that are nominally linear with an additive nonlinear component. Such systems…

Systems and Control · Electrical Eng. & Systems 2022-12-05 Rohan Sinha , James Harrison , Spencer M. Richards , Marco Pavone

Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-world testing is prohibitively expensive and unscalable.…

Machine Learning · Computer Science 2021-08-10 Aman Sinha , Matthew O'Kelly , Russ Tedrake , John Duchi

Without exact knowledge of the true system dynamics, optimal control of non-linear continuous-time systems requires careful treatment under epistemic uncertainty. In this work, we translate a probabilistic interpretation of the Pontryagin…

Machine Learning · Computer Science 2025-09-03 David Leeftink , Çağatay Yıldız , Steffen Ridderbusch , Max Hinne , Marcel van Gerven

Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to…

Optimization and Control · Mathematics 2020-10-01 Iman Shames , Farhad Farokhi

Balancing safety and efficiency when planning in crowded scenarios with uncertain dynamics is challenging where it is imperative to accomplish the robot's mission without incurring any safety violations. Typically, chance constraints are…

Robotics · Computer Science 2023-02-22 Khaled A. Mustafa , Oscar de Groot , Xinwei Wang , Jens Kober , Javier Alonso-Mora

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting.…

Machine Learning · Computer Science 2021-03-01 Jianyi Zhang , Paul Weng

This paper considers the problem of online multi-robot motion planning with general nonlinear dynamics subject to unknown external disturbances. We propose dSLAP, a distributed safe learning and planning framework that allows the robots to…

Systems and Control · Electrical Eng. & Systems 2025-05-27 Zhenyuan Yuan , Minghui Zhu

A fundamental challenge in learning to control an unknown dynamical system is to reduce model uncertainty by making measurements while maintaining safety. In this work, we formulate a mathematical definition of what it means to safely learn…

Optimization and Control · Mathematics 2020-11-25 Amir Ali Ahmadi , Abraar Chaudhry , Vikas Sindhwani , Stephen Tu

Despite the availability of ever more data enabled through modern sensor and computer technology, it still remains an open problem to learn dynamical systems in a sample-efficient way. We propose active learning strategies that leverage…

Machine Learning · Computer Science 2020-12-08 Mona Buisson-Fenet , Friedrich Solowjow , Sebastian Trimpe

We review the application of Statistical Mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward network learns from examples generated by a time dependent…

Disordered Systems and Neural Networks · Physics 2007-05-23 Renato Vicente , Osame Kinouchi , Nestor Caticha

Many automated system analysis techniques (e.g., model checking, model-based testing) rely on first obtaining a model of the system under analysis. System modeling is often done manually, which is often considered as a hindrance to adopt…

Software Engineering · Computer Science 2019-11-22 Jingyi Wang , Jun Sun , Qixia Yuan , Jun Pang

We develop a control algorithm that ensures the safety, in terms of confinement in a set, of a system with unknown, 2nd-order nonlinear dynamics. The algorithm establishes novel connections between data-driven and robust, nonlinear control.…

Systems and Control · Electrical Eng. & Systems 2021-05-17 Christos K. Verginis , Franck Djeumou , Ufuk Topcu

Many physical systems have underlying safety considerations that require that the policy employed ensures the satisfaction of a set of constraints. The analytical formulation usually takes the form of a Constrained Markov Decision Process…

Machine Learning · Computer Science 2021-03-03 Aria HasanzadeZonuzy , Archana Bura , Dileep Kalathil , Srinivas Shakkottai

Bayesian optimization has emerged as a highly effective tool for the safe online optimization of systems, due to its high sample efficiency and noise robustness. To further enhance its efficiency, reduced physical models of the system can…

Machine Learning · Computer Science 2024-06-18 Jannis O. Lübsen , Christian Hespe , Annika Eichler

We present a provably safe sampling-based motion planning algorithm for robotic systems affected by random disturbances of unknown distribution. We consider systems with linear or linearizable dynamics evolving in workspace with…

Robotics · Computer Science 2026-05-27 Ibon Gracia , Qi Heng Ho , Luca Laurenti , Morteza Lahijanian

We propose to leverage epistemic uncertainty about constraint satisfaction of a reinforcement learner in safety critical domains. We introduce a framework for specification of requirements for reinforcement learners in constrained settings,…

Artificial Intelligence · Computer Science 2021-02-09 Lenz Belzner , Martin Wirsing

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

Machine Learning · Computer Science 2022-03-17 Cong Lu , Philip J. Ball , Jack Parker-Holder , Michael A. Osborne , Stephen J. Roberts

On-line learning of probability distributions is analyzed from the field theoretical point of view. We can obtain an optimal on-line learning algorithm, since renormalization group enables us to control the number of degrees of freedom of a…

Disordered Systems and Neural Networks · Physics 2009-01-23 Toshiaki Aida

Safety is a critical issue in learning-based robotic and autonomous systems as learned information about their environments is often unreliable and inaccurate. In this paper, we propose a risk-aware motion control tool that is robust…

Robotics · Computer Science 2020-03-06 Astghik Hakobyan , Insoon Yang