This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining multiple modalities of human interaction. The current effort employs human demonstrations to teach a desired behavior via imitation learning, then leverages intervention data to correct for undesired behaviors produced by the imitation learner to teach novel tasks to an autonomous agent safely, after only minutes of training. We demonstrate this method in an autonomous perching task using a quadrotor with continuous roll, pitch, yaw, and throttle commands and imagery captured from a downward-facing camera in a high-fidelity simulated environment. Our method improves task completion performance for the same amount of human interaction when compared to learning from demonstrations alone, while also requiring on average 32% less data to achieve that performance. This provides evidence that combining multiple modes of human interaction can increase both the training speed and overall performance of policies for autonomous systems.
Nanyang Technological University（南洋理工大学）；Energy Research Institute, Nanyang Technological University（南洋理工大学能源研究院）
Decision-making is critical for lane change in autonomous driving. Reinforcement learning (RL) algorithms aim to identify the values of behaviors in various situations and thus they become a promising pathway to address the decision-making problem. However, poor runtime safety hinders RL-based decision-making strategies from complex driving tasks in practice. To address this problem, human demonstrations are incorporated into the RL-based decision-making strategy in this paper. Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the…
Baidu Inc.（百度公司）；City University of HongKong（香港城市大学）
Combining deep neural networks with reinforcement learning has shown great potential in the next-generation intelligent control. However, there are challenges in terms of safety and cost in practical applications. In this paper, we propose the Intervention Aided Reinforcement Learning (IARL) framework, which utilizes human intervened robot-environment interaction to improve the policy. We used the Unmanned Aerial Vehicle (UAV) as the test platform. We built neural networks as our policy to map sensor readings to control signals on the UAV. Our experiment scenarios cover both simulation and rea…
One Demonstration Is Enough for Real-World Robotic Reinforcement Learning
National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institution of Automation, Chinese Academy of Sciences（中国科学院自动化研究所复杂系统认知与决策智能国家重点实验室）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；PKU-PsiBot Joint Lab（北大-鹏城实验室联合实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
California Institute of Technology（加州理工学院）；University of California, Berkeley（加州大学伯克利分校）
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learning algorithm, Safety Augmented Value Estimation from Demonstrations (SAVED), which uses supervision that only identifies task completion and a modest set of suboptimal demonstrations to constrain exploration and learn efficiently while handling complex constraints. We then compare…
Safety has become one of the main challenges of applying deep reinforcement learning to real world systems. Currently, the incorporation of external knowledge such as human oversight is the only means to prevent the agent from visiting the catastrophic state. In this paper, we propose MBHI, a novel framework for safe model-based reinforcement learning, which ensures safety in the state-level and can effectively avoid both "local" and "non-local" catastrophes. An ensemble of supervised learners are trained in MBHI to imitate human blocking decisions. Similar to human decision-making process, MB…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；US Army Research Laboratory（美国陆军研究实验室）
Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state.…
University of Rochester（罗切斯特大学）；University of California San Diego（加州大学圣地亚哥分校）
Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert…
Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
Seoul National University（首尔大学）；ASRI（先进技术与科学研究院（ASRI））；Interdisciplinary Program in Artificial Intelligence（人工智能跨学科项目）；Department of Electrical and Computer Engineering（电气与计算机工程系）
Centre for Perceptual and Interactive Intelligence（感知与交互智能研究中心）；The Chinese University of Hong Kong（香港中文大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Human intervention is an effective way to inject human knowledge into the training loop of reinforcement learning, which can bring fast learning and ensured training safety. Given the very limited budget of human intervention, it remains challenging to design when and how human expert interacts with the learning agent in the training. In this work, we develop a novel human-in-the-loop learning method called Human-AI Copilot Optimization (HACO).To allow the agent's sufficient exploration in the risky environments while ensuring the training safety, the human expert can take over the control and…
Learning from Demonstration with Failure Awareness for Safe Robot Navigation
Department of Mechanical Engineering, The Hong Kong Polytechnic University（香港理工大学机械工程系）；College of Information Science and Technology, Eastern Institute of Technology（东华理工大学信息科学学院）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（香港理工大学航空与航空工程系）
SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
When learning common skills like driving, beginners usually have domain experts standing by to ensure the safety of the learning process. We formulate such learning scheme under the Expert-in-the-loop Reinforcement Learning where a guardian is introduced to safeguard the exploration of the learning agent. While allowing the sufficient exploration in the uncertain environment, the guardian intervenes under dangerous situations and demonstrates the correct actions to avoid potential accidents. Thus ERL enables both exploration and expert's partial demonstration as two training sources. Following…
Safe Remediation as Risk-Constrained Intervention Decision in Microservice Systems
School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；Khoury College of Computer Sciences, Northeastern University（美国东北大学库里计算机科学学院）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；College of Business and Economics, Australian National University（澳大利亚国立大学商业与经济学院）；School of Computer Science and Technology, Fujian Normal University（福建师范大学计算机科学与技术学院）
Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios. This can be attributed to the fact that current state-of-the-art, end-to-end reinforcement learning approaches still require thousands or millions of data samples to converge to a satisfactory policy and are subject to catastrophic failures during training. Conversely, in real world scenarios and after just a few data samples, humans are able to either provide demonstrations of the task, intervene to prevent catastrop…
Tsinghua University（清华大学）；University of Michigan（密歇根大学）
Safeguard functions such as those provided by advanced emergency braking (AEB) can provide another layer of safety for autonomous vehicles (AV). A smart safeguard function should adapt the activation conditions to the driving policy, to avoid unnecessary interventions as well as improve vehicle safety. This paper proposes a driving-policy adaptive safeguard (DPAS) design, including a collision avoidance strategy and an activation function. The collision avoidance strategy is designed in a reinforcement learning framework, obtained by Monte-Carlo Tree Search (MCTS). It can learn from past colli…
Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations
Shanghai Qizhi Institute（上海启智研究所）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息学院）；Mogo Auto Intelligence and Telematics Information Technology Co., Ltd（摩戈智能与 telemetry 信息技术有限公司）
One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing a novel active learning and control algorithm, SAFARI. During training, it allows an agent to request further human demonstrations when these out-of-distribution situations are met. At deployment, it combines model-free acting using behavioural cloning with model-based planning to reduce state-distribution shift, using future state reconstruction as a test …
Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and the agent has to derive a good policy by observing an expert's demonstrations. In this paper, we study the problem of how to make AL algorithms inherently safe while still meeting its learning objective. We consider a setting where the unknown reward function is assumed to be a linear combination of a set of state features, and the safety property is specified in Probabilistic Computation Tree Logic (PCTL). By embeddi…
University of Oxford（牛津大学）；Stanford University（斯坦福大学）
AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they haven't yet learned to avoid actions that could cause serious harm. How can an AI system explore and learn without making a single mistake that harms humans or otherwise causes serious damage? For model-free reinforcement learning, having a human "in the loop" and ready to intervene is currently the only way to prevent all catastrophes. We formalize human intervention for RL and show how to reduce the human labor required by training a supe…
Stanford Vision & Learning Lab（斯坦福视觉与学习实验室）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Imitation Learning is a promising paradigm for learning complex robot manipulation skills by reproducing behavior from human demonstrations. However, manipulation tasks often contain bottleneck regions that require a sequence of precise actions to make meaningful progress, such as a robot inserting a pod into a coffee machine to make coffee. Trained policies can fail in these regions because small deviations in actions can lead the policy into states not covered by the demonstrations. Intervention-based policy learning is an alternative that can address this issue -- it allows human operators …
DAISS: Phase-Aware Imitation Learning for Dual-Arm Robotic Ultrasound-Guided Interventions
Chair for Computer Aided Medical Procedures(CAMP), Technical University of Munich(TUM)（计算机辅助医疗程序主席职位（CAMP），慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；The University of Hong Kong(HKU)（香港大学）
Siemens Digital Industries Software（西门子数字工业软件）；KU Leuven（鲁汶大学）；Flanders Make（法兰德斯制造研究院）
To ensure user acceptance of autonomous vehicles (AVs), control systems are being developed to mimic human drivers from demonstrations of desired driving behaviors. Imitation learning (IL) algorithms serve this purpose, but struggle to provide safety guarantees on the resulting closed-loop system trajectories. On the other hand, Model Predictive Control (MPC) can handle nonlinear systems with safety constraints, but realizing human-like driving with it requires extensive domain knowledge. This work suggests the use of a seamless combination of the two techniques to learn safe AV controllers fr…
University of Bristol（布里斯托大学）；Bristol Robotics Laboratory（布里斯托机器人实验室）；Avian Technologies Ltd（Avian Technologies有限公司）
The success of the human-robot co-worker team in a flexible manufacturing environment where robots learn from demonstration heavily relies on the correct and safe operation of the robot. How this can be achieved is a challenge that requires addressing both technical as well as human-centric research questions. In this paper we discuss the state of the art in safety assurance, existing as well as emerging standards in this area, and the need for new approaches to safety assurance in the context of learning machines. We then focus on robotic learning from demonstration, the challenges these tech…
Asian Institute of Technology（亚洲理工学院）；The University of Tokyo（东京大学）
Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced Intervention-based Learning (ReIL), a framework consisting of a general intervention-based learning algorithm and a multi-task imitation learning model aimed at enabling non-expert users to train agents in real environments with little supervision or fine tuning. ReIL achieves this with an algorithm that combines the advantages of imitation learning and reinforcement learni…
Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications（北京邮电大学国家移动网络技术工程研究中心）；Nanyang Technological University（南洋理工大学）；Guangzhou University（广州大学）
Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection
Department of Electrical Engineering, Tsinghua University（电子工程系，清华大学）；Department of Electrical and Computer Engineering, University of Southern California（电气与计算机工程系，南加州大学）；Department of Aeronautics and Astronautics, Stanford University（航空与航天工程系，斯坦福大学）
Learning to effectively imitate human teleoperators, with generalization to unseen and dynamic environments, is a promising path to greater autonomy enabling robots to steadily acquire complex skills from supervision. We propose a new motion learning technique rooted in contraction theory and sum-of-squares programming for estimating a control law in the form of a polynomial vector field from a given set of demonstrations. Notably, this vector field is provably optimal for the problem of minimizing imitation loss while providing continuous-time guarantees on the induced imitation behavior. Our…
In this paper we present the first safe system for full control of self-driving vehicles trained from human demonstrations and deployed in challenging, real-world, urban environments. Current industry-standard solutions use rule-based systems for planning. Although they perform reasonably well in common scenarios, the engineering complexity renders this approach incompatible with human-level performance. On the other hand, the performance of machine-learned (ML) planning solutions can be improved by simply adding more exemplar data. However, ML methods cannot offer safety guarantees and someti…
