English
Related papers

Related papers: Safe Reinforcement Learning with Model Uncertainty…

200 papers

While reinforcement learning algorithms have had great success in the field of autonomous navigation, they cannot be straightforwardly applied to the real autonomous systems without considering the safety constraints. The later are crucial…

Robotics · Computer Science 2023-07-28 Brian Angulo , Gregory Gorbov , Aleksandr Panov , Konstantin Yakovlev

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement…

Machine Learning · Computer Science 2019-10-02 David Isele , Alireza Nakhaei , Kikuo Fujimura

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded…

Machine Learning · Statistics 2016-10-05 Yarin Gal , Zoubin Ghahramani

Providing an efficient strategy to navigate safely through unsignaled intersections is a difficult task that requires determining the intent of other drivers. We explore the effectiveness of Deep Reinforcement Learning to handle…

Artificial Intelligence · Computer Science 2018-02-28 David Isele , Reza Rahimi , Akansel Cosgun , Kaushik Subramanian , Kikuo Fujimura

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and…

Machine Learning · Computer Science 2023-09-12 Marin Vlastelica , Sebastian Blaes , Cristina Pineri , Georg Martius

A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from…

Machine Learning · Computer Science 2018-11-19 Rhiannon Michelmore , Marta Kwiatkowska , Yarin Gal

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Machine Learning · Computer Science 2025-09-09 Stephan Rabanser

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to implement the navigation pipeline functions, uncertainty estimation methods have become paramount for estimating confidence in DNN predictions. Bayesian Deep Learning…

Robotics · Computer Science 2023-01-16 Fabio Arnez , Huascar Espinoza , Ansgar Radermacher , François Terrier

Crash prediction is a critical component of road safety analyses. A widely adopted approach to crash prediction is application of regression based techniques. The underlying calibration process is often time-consuming, requiring significant…

Machine Learning · Computer Science 2018-12-20 Guangyuan Pan , Liping Fu , Lalita Thakali , Matthew Muresan , Ming Yu

We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value…

Machine Learning · Computer Science 2019-01-09 Andreas Sedlmeier , Thomas Gabor , Thomy Phan , Lenz Belzner , Claudia Linnhoff-Popien

Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to…

Cryptography and Security · Computer Science 2025-05-13 Mohammed Elnawawy , Gargi Mitra , Shahrear Iqbal , Karthik Pattabiraman

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby,…

Robotics · Computer Science 2021-01-26 Michael Everett , Yu Fan Chen , Jonathan P. How

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Machine Learning · Computer Science 2021-06-03 Omer Faruk Tuna , Ferhat Ozgur Catak , M. Taner Eskil

Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we predict pedestrians by emulating their own motion planning. From online observations, we infer a mixture density…

Computer Vision and Pattern Recognition · Computer Science 2017-06-21 Eike Rehder , Florian Wirth , Martin Lauer , Christoph Stiller

Mobile robots navigating in crowds trained using reinforcement learning are known to suffer performance degradation when faced with out-of-distribution scenarios. We propose that by properly accounting for the uncertainties of pedestrians,…

Robotics · Computer Science 2025-08-08 Jianpeng Yao , Xiaopan Zhang , Yu Xia , Zejin Wang , Amit K. Roy-Chowdhury , Jiachen Li

In safety-critical systems that interface with the real world, the role of uncertainty in decision-making is pivotal, particularly in the context of machine learning models. For the secure functioning of Cyber-Physical Systems (CPS), it is…

Machine Learning · Computer Science 2024-04-29 Neha Kumari , Sumit Kumar. Sneha Priya , Ayush Kumar , Akash Fogla

Past research on pedestrian trajectory forecasting mainly focused on deterministic predictions which provide only point estimates of future states. These future estimates can help an autonomous vehicle plan its trajectory and avoid…

Machine Learning · Computer Science 2023-01-16 Anshul Nayak , Azim Eskandarian , Zachary Doerzaph

This paper presents a novel model-reference reinforcement learning control method for uncertain autonomous surface vehicles. The proposed control combines a conventional control method with deep reinforcement learning. With the conventional…

Systems and Control · Electrical Eng. & Systems 2021-06-17 Qingrui Zhang , Wei Pan , Vasso Reppa

Uncertainty estimation (UE) techniques -- such as the Gaussian process (GP), Bayesian neural networks (BNN), Monte Carlo dropout (MCDropout) -- aim to improve the interpretability of machine learning models by assigning an estimated…

Machine Learning · Computer Science 2021-12-10 Yehao Liu , Matteo Pagliardini , Tatjana Chavdarova , Sebastian U. Stich

The automated real-time recognition of unexpected situations plays a crucial role in the safety of autonomous vehicles, especially in unsupported and unpredictable scenarios. This paper evaluates different Bayesian uncertainty…

Machine Learning · Computer Science 2025-02-14 Ruben Grewal , Paolo Tonella , Andrea Stocco