English
Related papers

Related papers: Safe Inverse Reinforcement Learning via Control Ba…

200 papers

Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free…

Systems and Control · Electrical Eng. & Systems 2024-08-14 Homayoun Honari , Mehran Ghafarian Tamizi , Homayoun Najjaran

This paper addresses learning safe output feedback control laws from partial observations of expert demonstrations. We assume that a model of the system dynamics and a state estimator are available along with corresponding error bounds,…

Systems and Control · Electrical Eng. & Systems 2024-04-04 Lars Lindemann , Alexander Robey , Lejun Jiang , Satyajeet Das , Stephen Tu , Nikolai Matni

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby…

Machine Learning · Computer Science 2024-12-16 Mark Beliaev , Ramtin Pedarsani

In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety…

Machine Learning · Computer Science 2024-06-14 Zhepeng Cen , Yihang Yao , Zuxin Liu , Ding Zhao

The sample inefficiency of reinforcement learning (RL) remains a significant challenge in robotics. RL requires large-scale simulation and can still cause long training times, slowing research and innovation. This issue is particularly…

Robotics · Computer Science 2026-01-16 Johannes Heeg , Yunlong Song , Davide Scaramuzza

In this paper we seek to quantify the ability of learning to improve safety guarantees endowed by Control Barrier Functions (CBFs). In particular, we investigate how model uncertainty in the time derivative of a CBF can be reduced via…

Systems and Control · Electrical Eng. & Systems 2020-11-20 Andrew J. Taylor , Andrew Singletary , Yisong Yue , Aaron D. Ames

The ability to recover from a fall is an essential feature for a legged robot to navigate in challenging environments robustly. Until today, there has been very little progress on this topic. Current solutions mostly build upon…

Robotics · Computer Science 2024-12-20 Joonho Lee , Jemin Hwangbo , Marco Hutter

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

Machine Learning · Computer Science 2026-05-25 Chenglin Li , Grant Ruan , Hua Geng

Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically lack safety guarantees, especially when the robot and…

Robotics · Computer Science 2022-11-22 Mahmoud Selim , Amr Alanwar , Shreyas Kousik , Grace Gao , Marco Pavone , Karl H. Johansson

This paper addresses the problem of safety-critical control for non-affine control systems. It has been shown that optimizing quadratic costs subject to state and control constraints can be sub-optimally reduced to a sequence of quadratic…

Systems and Control · Electrical Eng. & Systems 2024-02-15 Wei Xiao , Ross Allen , Daniela Rus

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

Machine Learning · Computer Science 2025-01-03 Ondrej Bajgar , Sid William Gould , Rohan Narayan Langford Mitta , Jonathon Liu , Oliver Newcombe , Jack Golden

We consider the problem of safely exploring a static and unknown environment while learning valid control barrier functions (CBFs) from sensor data. Existing works either assume known environments, target specific dynamics models, or use…

Systems and Control · Electrical Eng. & Systems 2025-04-03 Paul Lutkus , Deepika Anantharaman , Stephen Tu , Lars Lindemann

Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce…

Machine Learning · Computer Science 2023-12-19 Lauren H. Cooke , Harvey Klyne , Edwin Zhang , Cassidy Laidlaw , Milind Tambe , Finale Doshi-Velez

Designing safety-critical control for robotic manipulators is challenging, especially in a cluttered environment. First, the actual trajectory of a manipulator might deviate from the planned one due to the complex collision environments and…

Robotics · Computer Science 2022-11-14 Xuda Ding , Han Wang , Yi Ren , Yu Zheng , Cailian Chen , Jianping He

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Machine Learning · Computer Science 2026-04-28 Bilgehan Sel , Vaishakh Keshava , Phillip Wallis , Lukas Rutishauser , Ming Jin , Dingcheng Li

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are…

Robotics · Computer Science 2026-03-10 Bojan Derajić , Sebastian Bernhard , Wolfgang Hönig

Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL)…

Systems and Control · Electrical Eng. & Systems 2026-05-05 Ashik Abrar Naeem , Mohammad Ariful Haque

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

This paper presents a deep reinforcement learning (DRL) framework for active flow control (AFC) to reduce drag in aerodynamic bodies. Tested on a 3D cylinder at Re = 100, the DRL approach achieved a 9.32% drag reduction and a 78.4% decrease…

Machine Learning · Computer Science 2024-11-11 Ricard Montalà , Bernat Font , Pol Suárez , Jean Rabault , Oriol Lehmkuhl , Ivette Rodriguez

Cyber-physical systems (CPS) require the joint optimization of discrete cyber actions and continuous physical parameters under stringent safety logic constraints. However, existing hierarchical approaches often compromise global optimality,…

Machine Learning · Computer Science 2025-11-04 Guangxi Wan , Peng Zeng , Xiaoting Dong , Chunhe Song , Shijie Cui , Dong Li , Qingwei Dong , Yiyang Liu , Hongfei Bai