Learning to Fly via Deep Model-Based Reinforcement Learning
Volkswagen Group, Machine Learning Research Lab（大众集团机器学习研究实验室）；Technical University of Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Philip Becker-Ehmck, Maximilian Karl, Jan Peters, Patrick van der Smagt
Learning to control robots without requiring engineered models has been a long-term goal, promising diverse and novel applications. Yet, reinforcement learning has only achieved limited impact on real-time robot control due to its high demand of real-world interactions. In this work, by leveraging a learnt probabilistic model of drone dynamics, we learn a thrust-attitude controller for a quadrotor through model-based reinforcement learning. No prior knowledge of the flight dynamics is assumed; instead, a sequential latent variable model, used generatively and as an online filter, is learnt from raw sensory input. The controller and value function are optimised entirely by propagating stochastic analytic gradients through generated latent trajectories. We show that "learning to fly" can be achieved with less than 30 minutes of experience with a single drone, and can be deployed solely using onboard computational resources and sensors, on a self-built drone.
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of expert data and knowledge based data aggregation is integrated into the RL process to aid convergence. Experimentation is carried out on a Parrot AR drone in different indoor arenas and the results are compared with other baseline technologies. We demonstrate how the drone succe…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Microsoft Research（微软研究院）
Assemblies of modular subsystems are being pressed into service to perform sensing, reasoning, and decision making in high-stakes, time-critical tasks in such areas as transportation, healthcare, and industrial automation. We address the opportunity to maximize the utility of an overall computing system by employing reinforcement learning to guide the configuration of the set of interacting modules that comprise the system. The challenge of doing system-wide optimization is a combinatorial problem. Local attempts to boost the performance of a specific module by modifying its configuration ofte…
Pohang University of Science and Technology（浦项科技大学）
An integrated framework of computational fluid-structural dynamics (CFD-CSD) and deep reinforcement learning (deep-RL) is developed for control of a fly-scale flexible-winged flyer in complex flow. Dynamics of the flyer in complex flow is highly unsteady and nonlinear, which makes modeling the dynamics challenging. Thus, conventional control methodologies, where the dynamics is modeled, are insufficient for regulating such complicated dynamics. Therefore, in the present study, the integrated framework, in which the whole governing equations for fluid and structure are solved, is proposed to ge…
University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Cambridge（剑桥大学）
Robotic simulators are crucial for academic research and education as well as the development of safety-critical applications. Reinforcement learning environments -- simple simulations coupled with a problem specification in the form of a reward function -- are also important to standardize the development (and benchmarking) of learning algorithms. Yet, full-scale simulators typically lack portability and parallelizability. Vice versa, many reinforcement learning environments trade-off realism for high sample throughputs in toy-like problems. While public data sets have greatly benefited deep …
Allen Institute for AI（艾伦人工智能研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In practice, imitation learning is preferred over pure reinforcement learning whenever it is possible to design a teaching agent to provide expert supervision. However, we show that when the teaching agent makes decisions with access to privileged information that is unavailable to the student, this information is marginalized during imitation learning, resulting in an "imitation gap" and, potentially, poor results. Prior work bridges this gap via a progression from imitation learning to reinforcement learning. While often successful, gradual progression fails for tasks that require frequent s…
EURECOM（欧洲通信学院）；Technical University of Munich（慕尼黑工业大学）
Autonomous deployment of unmanned aerial vehicles (UAVs) supporting next-generation communication networks requires efficient trajectory planning methods. We propose a new end-to-end reinforcement learning (RL) approach to UAV-enabled data collection from Internet of Things (IoT) devices in an urban environment. An autonomous drone is tasked with gathering data from distributed sensor nodes subject to limited flying time and obstacle avoidance. While previous approaches, learning and non-learning based, must perform expensive recomputations or relearn a behavior when important scenario paramet…
Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study
Department of Applied and Computational Mathematics and Statistics, University of Notre Dame（应用与计算数学与统计学系，圣约翰大学）；Department of Pediatrics (Cardiology), Stanford University（儿科（心脏病学）系，斯坦福大学）；Department of Bioengineering, Stanford University（生物工程系，斯坦福大学）
University of Pennsylvania（宾夕法尼亚大学）；Deapartment of Computer and Information Science（计算机与信息科学系）
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks. A key problem is how to ensure safety of the learned policy---e.g., that a walking robot does not fall over or that an autonomous car does not run into an obstacle. We focus on the setting where the dynamics are known, and the goal is to ensure that a policy trained in simulation satisfies a given safety constraint. We propose an approach, called model predictive shielding (MPS), that switches on-the-fly between a learned policy and a backup policy to ensure safety. We prove that our approac…
Recent advances in Reinforcement Learning, grounded on combining classical theoretical results with Deep Learning paradigm, led to breakthroughs in many artificial intelligence tasks and gave birth to Deep Reinforcement Learning (DRL) as a field of research. In this work latest DRL algorithms are reviewed with a focus on their theoretical justification, practical limitations and observed empirical properties.
Navigating Assistance System for Quadcopter with Deep Reinforcement Learning
National Cheng Kung University（国立成功大学）；Research Laboratories（研究实验室）；Industrial Technology Research Institute（工业技术研究 institutes）；Department of Computer Science（计算机科学系）；Information Engineering（信息工程系）；National Taitung University（国立台东大学）
Stevens Institute of Technology（斯蒂文斯理工学院）；University of Carthage（迦太基大学）
In this paper, we propose an autonomous UAV path planning framework using deep reinforcement learning approach. The objective is to employ a self-trained UAV as a flying mobile unit to reach spatially distributed moving or static targets in a given three dimensional urban area. In this approach, a Deep Deterministic Policy Gradient (DDPG) with continuous action space is designed to train the UAV to navigate through or over the obstacles to reach its assigned target. A customized reward function is developed to minimize the distance separating the UAV and its destination while penalizing collis…
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct an on-the-fly synchronised product with the MDP and the finite machine. The temporal structure acts as a guide for the RL agent within the product, where a modular Deep Deterministic Policy Gradient (DDPG) architecture is proposed to generate a low-level control policy. We evalua…
We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the model-free Q-learning objective, we show that DEVI's model-based internal structure provides `one-shot' transfer to changes in reward and transition structure, even for tasks with very high-dimensional state spaces.
Aiming at a comprehensive and concise tutorial survey, recap of variational inference and reinforcement learning with Probabilistic Graphical Models are given with detailed derivations. Reviews and comparisons on recent advances in deep reinforcement learning are made from various aspects. We offer detailed derivations to a taxonomy of Probabilistic Graphical Model and Variational Inference methods in deep reinforcement learning, which serves as a complementary material on top of the original contributions.
Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more. This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques. Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the r…
National University of Ireland, Galway（爱尔兰国立大学戈尔韦分校）
In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This chapter reviews the recent advances in deep reinforcement learning with a focus on the most used deep architectures such as autoe…
Training agents in cooperative settings offers the promise of AI agents able to interact effectively with humans (and other agents) in the real world. Multi-agent reinforcement learning (MARL) has the potential to achieve this goal, demonstrating success in a series of challenging problems. However, whilst these advances are significant, the vast majority of focus has been on the self-play paradigm. This often results in a coordination problem, caused by agents learning to make use of arbitrary conventions when playing with themselves. This means that even the strongest self-play agents may ha…
Visual exploration and smart data collection via autonomous vehicles is an attractive topic in various disciplines. Disturbances like wind significantly influence both the power consumption of the flying robots and the performance of the camera. We propose a reinforcement learning approach which combines the effects of the power consumption and the object detection modules to develop a policy for object detection in large areas with limited battery life. The learning model enables dynamic learning of the negative rewards of each action based on the drag forces that is resulted by the motion of…
We propose DeepSim, a reinforcement learning environment build toolkit for ROS and Gazebo. It allows machine learning or reinforcement learning researchers to access the robotics domain and create complex and challenging custom tasks in ROS and Gazebo simulation environments. This toolkit provides building blocks of advanced features such as collision detection, behaviour control, domain randomization, spawner, and many more. DeepSim is designed to reduce the boundary between robotics and machine learning communities by providing Python interface. In this paper, we discuss the components and d…
Delft University of Technology（代尔夫特理工大学）；Czech Technical University in Prague（布拉格捷克理工大学）
Landing a quadrotor on an inclined surface is a challenging maneuver. The final state of any inclined landing trajectory is not an equilibrium, which precludes the use of most conventional control methods. We propose a deep reinforcement learning approach to design an autonomous landing controller for inclined surfaces. Using the proximal policy optimization (PPO) algorithm with sparse rewards and a tailored curriculum learning approach, an inclined landing policy can be trained in simulation in less than 90 minutes on a standard laptop. The policy then directly runs on a real Crazyflie 2.1 qu…
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field of AutoRL, which seeks to automate design decisions to create more general algorithms. Recent work suggests that population based approaches may be effective AutoRL algorithms, by learning hyperparameter schedules on the fly. In particular, the PB2 algorithm is able to achieve strong performance in RL tasks by formulating online hyperparameter optimization as time varying GP-bandit problem, while also providing theor…
The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision boundary geometry and the loss landscape of neural policies is still quite limited. In this paper we propose a framework to investigate the decision boundary and loss landscape similarities across states and across MDPs. We conduct experiments in various games from Arcade Learning Environment, and discover that high sensitivity directions for neural policies are correlated across MDPs. We argue that these high sensi…
University of California, Berkeley（加州大学伯克利分校）；Simon Fraser University（西蒙弗雷泽大学）；Georgia Institute of Technology（佐治亚理工学院）
We present a reinforcement learning (RL) framework that enables quadrupedal robots to perform soccer goalkeeping tasks in the real world. Soccer goalkeeping using quadrupeds is a challenging problem, that combines highly dynamic locomotion with precise and fast non-prehensile object (ball) manipulation. The robot needs to react to and intercept a potentially flying ball using dynamic locomotion maneuvers in a very short amount of time, usually less than one second. In this paper, we propose to address this problem using a hierarchical model-free RL framework. The first component of the framewo…
Unmanned Aerial Vehicles (UAVs) have attracted considerable research interest recently. Especially when it comes to the realm of Internet of Things, the UAVs with Internet connectivity are one of the main demands. Furthermore, the energy constraint i.e. battery limit is a bottle-neck of the UAVs that can limit their applications. We try to address and solve the energy problem. Therefore, a path planning method for a cellular-connected UAV is proposed that will enable the UAV to plan its path in an area much larger than its battery range by getting recharged in certain positions equipped with p…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
Recent developments in deep reinforcement learning have enabled the creation of agents for solving a large variety of games given a visual input. These methods have been proven successful for 2D games, like the Atari games, or for simple tasks, like navigating in mazes. It is still an open question, how to address more complex environments, in which the reward is sparse and the state space is huge. In this paper we propose a divide and conquer deep reinforcement learning solution and we test our agent in the first person shooter (FPS) game of Doom. Our work is based on previous works in deep r…
The Charles Stark Draper Laboratory, Inc.（查尔斯·斯塔克·德雷珀实验室公司）
Knowledge of the symmetries of reinforcement learning (RL) systems can be used to create compressed and semantically meaningful representations of a low-level state space. We present a method of automatically detecting RL symmetries directly from raw trajectory data without requiring active control of the system. Our method generates candidate symmetries and trains a recurrent neural network (RNN) to discriminate between the original trajectories and the transformed trajectories for each candidate symmetry. The RNN discriminator's accuracy for each candidate reveals how symmetric the system is…
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area of research and many concurrent inventions, we decided to focus on a relatively simple robotic task to evaluate a set of ideas that might help to solve recent reinforcement learning problems. We test a newly created combination of two commonly used reinforcement learning methods, whether it is able to learn more effectively than a baseline. We also compare d…
DEI - CNIT University of Bologna（博洛尼亚大学 DEI - CNIT）；CNR-IEIIT（意大利国家研究委员会电子、信息工程与电信研究所）；ECE Department Stony Brook University（石溪大学电子与计算机工程系）
In this paper, we study a joint detection, mapping and navigation problem for a single unmanned aerial vehicle (UAV) equipped with a low complexity radar and flying in an unknown environment. The goal is to optimize its trajectory with the purpose of maximizing the mapping accuracy and, at the same time, to avoid areas where measurements might not be sufficiently informative from the perspective of a target detection. This problem is formulated as a Markov decision process (MDP) where the UAV is an agent that runs either a state estimator for target detection and for environment mapping, and a…
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinf…
Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural networks. Yet the observed degradation in policy performance caused by imperceptible worst-case policy dependent translations along high sensitivity directions (i.e. adversarial perturbations) raises concerns on the robustness of deep reinforcement learning policies. In our paper, we show that these high sensitivity directions do not lie only along particular worst-case directions, but rather are more abundant in the deep neural policy landscape …
Collision avoidance is a crucial task in vision-guided autonomous navigation. Solutions based on deep reinforcement learning (DRL) has become increasingly popular. In this work, we proposed several novel agent state and reward function designs to tackle two critical issues in DRL-based navigation solutions: 1) smoothness of the trained flight trajectories; and 2) model generalization to handle unseen environments. Formulated under a DRL framework, our model relies on margin reward and smoothness constraints to ensure UAVs fly smoothly while greatly reducing the chance of collision. The propose…
Tsinghua University（清华大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general reinforcement learning paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance. In this paper, we present IQ, i.e., interference-aware deep Q-learning, to mitigate catastrophic inter…
Deep reinforcement learning has become popular over recent years, showing superiority on different visual-input tasks such as playing Atari games and robot navigation. Although objects are important image elements, few work considers enhancing deep reinforcement learning with object characteristics. In this paper, we propose a novel method that can incorporate object recognition processing to deep reinforcement learning models. This approach can be adapted to any existing deep reinforcement learning frameworks. State-of-the-art results are shown in experiments on Atari games. We also propose a…
We explore the use of deep learning and deep reinforcement learning for optimization problems in transportation. Many transportation system analysis tasks are formulated as an optimization problem - such as optimal control problems in intelligent transportation systems and long term urban planning. Often transportation models used to represent dynamics of a transportation system involve large data sets with complex input-output interactions and are difficult to use in the context of optimization. Use of deep learning metamodels can produce a lower dimensional representation of those relations …
University of Amsterdam（阿姆斯特丹大学）；UvA-Bosch Delta Lab（阿姆斯特丹大学-博世德尔塔实验室）；Informatics Institute（信息学研究所）
Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance…
Deep Reinforcement Learning has emerged as an efficient dynamic obstacle avoidance method in highly dynamic environments. It has the potential to replace overly conservative or inefficient navigation approaches. However, the integration of Deep Reinforcement Learning into existing navigation systems is still an open frontier due to the myopic nature of Deep-Reinforcement-Learning-based navigation, which hinders its widespread integration into current navigation systems. In this paper, we propose the concept of an intermediate planner to interconnect novel Deep-Reinforcement-Learning-based obst…
