Safety-Aware Hardening of 3D Object Detection Neural Network Systems
DENSO AUTOMOTIVE Deutschland GmbH（电装汽车德国有限公司）
Chih-Hong Cheng
备注：
This version is similar to v1 with an added statement: "The evaluation using KITTI dataset in this paper is for knowledge dissemination and scientific publication and is not for commercial use"
We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the capability of other components) that partitions the 3D input space by criticality, where the critical area employs a separate criterion on robustness under perturbation, quality of bounding boxes, and the tolerance over false negatives demonstrated on the training set. In the architecture design, we consider symbolic error propagation to allow feature-level perturbation. Subsequently, we introduce a specialized loss function reflecting (1) the safety specification, (2) the use of single-stage detection architecture, and finally, (3) the characterization of robustness under perturbation. We also replace the commonly seen non-max-suppression post-processing algorithm by a safety-aware non-max-inclusion algorithm, in order to maintain the safety claim created by the neural network. The concept is detailed by extending the state-of-the-art PIXOR detector which creates object bounding boxes in bird's eye view with inputs from point clouds.
Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs (HJI) PDEs. Self-supervised learning has been used to approximate solutions of such PDEs while circumventing the curse of dimensionality. However, this method fails to learn discontinuous PDE solutions due to its sampling nature, leading to poor safety performance of the resulting controllers in robotics applications when player rewards are discontinuous. This paper investigates two potential solutions to this problem: a hybrid method that leverages both supervised Nash equilibria and th…
Polytechnic of Torino（都灵理工大学）；Univ Rennes（雷恩大学）；INRIA（法国国家信息与自动化研究所）；University of Trento（特伦托大学）
Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving. However, recent findings indicate that transient hardware faults may corrupt the models prediction dramatically. For instance, the radiation-induced misprediction probability can be so high to impede a safe deployment of DNNs models at scale, urging the need for efficient and effective hardening solutions. In this work, we propose to tackle the reliability issue both at training and model design time. First, we show that van…
A Fairness-Aware Strategy for B5G Physical-layer Security Leveraging Reconfigurable Intelligent Surfaces
SAMOVAR, T\'el\'ecom SudParis, Institut Polytechnique de Paris, Palaiseau, France Carleton University, School of Computer Science, Ottawa, Canada Politecnico di Bari, Dipartimento di Ingegneria Elettrica e dell'Informazione, Italy
SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
West China Biomedical Big Data Center, West China Hospital, SCU（西昌生物医学大数据中心、西昌医院、SCU）；NTU；USTC；TeleAI, China Telecom（TeleAI、中国电信）；BUPT；Tsinghua University（清华大学）；HKUST(Guangzhou)（HKUST（广州））
Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）；Sun Yat-sen University（中山大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）
Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety constraints. However, few studies have addressed the non-stationary disturbances in the environments, which may cause catastrophic outcomes. In this paper, we propose the context-aware safe reinforcement learning (CASRL) method, a meta-learning framework to realize safe adaptation in non-stationary environments. We use a probabilistic latent variable model to ac…
Imperial College London（伦敦帝国理工学院）；University College London（伦敦大学学院）；Apricity
The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness. In recent years, a variety of approaches have been put forward to address the challenges of safety-aware reinforcement learning; however, these methods often either require a handcrafted model of the environment to be provided beforehand, or that the environment is relatively simple and low-dimensional. We present a novel approach to safety-aware deep reinforcement learning in high-dimensional environments called l…
In this paper, we consider the setting of piecewise i.i.d. bandits under a safety constraint. In this piecewise i.i.d. setting, there exists a finite number of changepoints where the mean of some or all arms change simultaneously. We introduce the safety constraint studied in \citet{wu2016conservative} to this setting such that at any round the cumulative reward is above a constant factor of the default action reward. We propose two actively adaptive algorithms for this setting that satisfy the safety constraint, detect changepoints, and restart without the knowledge of the number of changepoi…
Department of Computer Science, University of Memphis（孟菲斯大学计算机科学系）；University of Memphis（孟菲斯大学）
We present a novel adaptive cruise control (ACC) system namely SAINT-ACC: {S}afety-{A}ware {Int}elligent {ACC} system (SAINT-ACC) that is designed to achieve simultaneous optimization of traffic efficiency, driving safety, and driving comfort through dynamic adaptation of the inter-vehicle gap based on deep reinforcement learning (RL). A novel dual RL agent-based approach is developed to seek and adapt the optimal balance between traffic efficiency and driving safety/comfort by effectively controlling the driving safety model parameters and inter-vehicle gap based on macroscopic and microscopi…
Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints. Typical for such systems, however, is to have their controllers designed with formal guarantees on safety that precede in priority such optimizations, which in turn limits their application in real settings. In this paper, we propose a novel energy optimization framework that is aware of the autonomous system's safety state, and leverages it to regulate the application of energy optimization methods so that the system's formal safety…
Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；University of Patras（帕特雷大学）
The recently introduced Intelligent Trial-and-Error (IT&E) algorithm showed that robots can adapt to damage in a matter of a few trials. The success of this algorithm relies on two components: prior knowledge acquired through simulation with an intact robot, and Bayesian optimization (BO) that operates on-line, on the damaged robot. While IT&E leads to fast damage recovery, it does not incorporate any safety constraints that prevent the robot from attempting harmful behaviors. In this work, we address this limitation by replacing the BO component with a constrained BO procedure. We evaluate ou…
Graz University of Technology（格拉茨工业大学）；Pro2Future GmbH（Pro2Future有限公司）；Technical University of Munich（慕尼黑工业大学）；Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；Technical University of Vienna（维也纳工业大学）；Vienna University of Economics and Business（维也纳经济大学）；Center for Digital Production GmbH（数字生产中心有限公司）
Industrial Safety deals with the physical integrity of humans, machines and the environment when they interact during production scenarios. Industrial Safety is subject to a rigorous certification process that leads to inflexible settings, in which all changes are forbidden. With the progressing introduction of smart robotics and smart machinery to the factory floor, combined with an increasing shortage of skilled workers, it becomes imperative that safety scenarios incorporate a flexible handling of the boundary between humans, machines and the environment. In order to increase the well-being…
As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired side effects while executing a policy on a primary task. Since one can define multiple tasks for a given environment dynamics, there are two important challenges. First, we need to abstract the concept of safety that applies broadly to that environment independent of the specific task being executed. Second, we need a mechanism for the abstracted notion of saf…
Despite the rapid improvement of autonomous driving technology in recent years, automotive manufacturers must resolve liability issues to commercialize autonomous passenger car of SAE J3016 Level 3 or higher. To cope with the product liability law, manufacturers develop autonomous driving systems in compliance with international standards for safety such as ISO 26262 and ISO 21448. Concerning the safety of the intended functionality (SOTIF) requirement in ISO 26262, the driving policy recommends providing an explicit rational basis for maneuver decisions. In this case, mathematical models such…
Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics
Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University（机械工程数据科学研究所（DSME），亚琛工业大学）；Institute of Climate and Energy Systems (ICE), Energy Systems Engineering (ICE-1), Forschungszentrum Jülich GmbH（气候与能源系统研究所（ICE），能源系统工程（ICE-1），焦耳研究中心有限公司）
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；School of Computer Science & Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）
Our objective of this project is to make the extension based on the technique mentioned in the paper "Safety-Aware Apprenticeship Learning" to improve the utility and the efficiency of the existing Reinforcement Learning model from a Single-Agent Learning framework to a Multi-Agent Learning framework. Our contributions to the project are presented in the following bullet points: 1. Regarding the fact that we will add an extension to the Inverse Reinforcement Learning model from a Single-Agent scenario to a Multi-Agentscenario. Our first contribution to this project is considering the case of e…
