可靠的导航系统在机器人技术和自动驾驶中具有广泛的应用。当前方法采用开环过程,将传感器输入直接转换为动作。但是,这些开环方案由于概括不佳而在处理复杂而动态的现实情况方面具有挑战性。在模仿人类导航的情况下,我们添加了一个推理过程,将动作转换回内部潜在状态,形成了两阶段的感知,决策和推理的封闭环路。首先,VAE增强的演示学习赋予了模型对基本导航规则的理解。然后,在RL增强交互学习中的两个双重过程彼此产生奖励反馈,并共同增强了避免障碍能力。推理模型可以实质上促进概括和鲁棒性,并促进算法将算法的部署到现实世界的机器人,而无需精心转移。实验表明,与最先进的方法相比,我们的方法更适合新型方案。
translated by 谷歌翻译
尽管数十年的努力,但在真正的情景中的机器人导航具有波动性,不确定性,复杂性和歧义(vuca短暂),仍然是一个具有挑战性的话题。受到中枢神经系统(CNS)的启发,我们提出了一个在Vuca环境中的自主导航的分层多专家学习框架。通过考虑目标位置,路径成本和安全水平的启发式探索机制,上层执行同时映射探索和路线规划,以避免陷入盲巷,类似于CNS中的大脑。使用本地自适应模型融合多种差异策略,下层追求碰撞 - 避免和直接策略之间的平衡,作为CNS中的小脑。我们在多个平台上进行仿真和实际实验,包括腿部和轮式机器人。实验结果表明我们的算法在任务成就,时间效率和安全性方面优于现有方法。
translated by 谷歌翻译
深度强化学习在基于激光的碰撞避免有效的情况下取得了巨大的成功,因为激光器可以感觉到准确的深度信息而无需太多冗余数据,这可以在算法从模拟环境迁移到现实世界时保持算法的稳健性。但是,高成本激光设备不仅很难为大型机器人部署,而且还表现出对复杂障碍的鲁棒性,包括不规则的障碍,例如桌子,桌子,椅子和架子,以及复杂的地面和特殊材料。在本文中,我们提出了一个新型的基于单眼相机的复杂障碍避免框架。特别是,我们创新地将捕获的RGB图像转换为伪激光测量,以进行有效的深度强化学习。与在一定高度捕获的传统激光测量相比,仅包含距离附近障碍的一维距离信息,我们提议的伪激光测量融合了捕获的RGB图像的深度和语义信息,这使我们的方法有效地有效障碍。我们还设计了一个功能提取引导模块,以加重输入伪激光测量,并且代理对当前状态具有更合理的关注,这有利于提高障碍避免政策的准确性和效率。
translated by 谷歌翻译
这项工作研究了图像目标导航问题,需要通过真正拥挤的环境引导具有嘈杂传感器和控制的机器人。最近的富有成效的方法依赖于深度加强学习,并学习模拟环境中的导航政策,这些环境比真实环境更简单。直接将这些训练有素的策略转移到真正的环境可能非常具有挑战性甚至危险。我们用由四个解耦模块组成的分层导航方法来解决这个问题。第一模块在机器人导航期间维护障碍物映射。第二个将定期预测实时地图上的长期目标。第三个计划碰撞命令集以导航到长期目标,而最终模块将机器人正确靠近目标图像。四个模块是单独开发的,以适应真实拥挤的情景中的图像目标导航。此外,分层分解对导航目标规划,碰撞避免和导航结束预测的学习进行了解耦,这在导航训练期间减少了搜索空间,并有助于改善以前看不见的真实场景的概括。我们通过移动机器人评估模拟器和现实世界中的方法。结果表明,我们的方法优于多种导航基线,可以在这些方案中成功实现导航任务。
translated by 谷歌翻译
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.
translated by 谷歌翻译
Autonomous navigation in crowded spaces poses a challenge for mobile robots due to the highly dynamic, partially observable environment. Occlusions are highly prevalent in such settings due to a limited sensor field of view and obstructing human agents. Previous work has shown that observed interactive behaviors of human agents can be used to estimate potential obstacles despite occlusions. We propose integrating such social inference techniques into the planning pipeline. We use a variational autoencoder with a specially designed loss function to learn representations that are meaningful for occlusion inference. This work adopts a deep reinforcement learning approach to incorporate the learned representation for occlusion-aware planning. In simulation, our occlusion-aware policy achieves comparable collision avoidance performance to fully observable navigation by estimating agents in occluded spaces. We demonstrate successful policy transfer from simulation to the real-world Turtlebot 2i. To the best of our knowledge, this work is the first to use social occlusion inference for crowd navigation.
translated by 谷歌翻译
Despite some successful applications of goal-driven navigation, existing deep reinforcement learning-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-art baselines. Demonstration videos are available at \colorb{https://youtu.be/93LGlGvaN0c.
translated by 谷歌翻译
我们介绍了一个目标驱动的导航系统,以改善室内场景中的Fapless视觉导航。我们的方法在每次步骤中都将机器人和目标的多视图观察为输入,以提供将机器人移动到目标的一系列动作,而不依赖于运行时在运行时。通过优化包含三个关键设计的组合目标来了解该系统。首先,我们建议代理人在做出行动决定之前构建下一次观察。这是通过从专家演示中学习变分生成模块来实现的。然后,我们提出预测预先预测静态碰撞,作为辅助任务,以改善导航期间的安全性。此外,为了减轻终止动作预测的训练数据不平衡问题,我们还介绍了一个目标检查模块来区分与终止动作的增强导航策略。这三种建议的设计都有助于提高培训数据效率,静态冲突避免和导航泛化性能,从而产生了一种新颖的目标驱动的FLASES导航系统。通过对Turtlebot的实验,我们提供了证据表明我们的模型可以集成到机器人系统中并在现实世界中导航。视频和型号可以在补充材料中找到。
translated by 谷歌翻译
我们提出了一种新的方法,以改善基于深入强化学习(DRL)的室外机器人导航系统的性能。大多数现有的DRL方法基于精心设计的密集奖励功能,这些功能可以学习环境中的有效行为。我们仅通过稀疏的奖励(易于设计)来解决这个问题,并提出了一种新颖的自适应重尾增强算法,用于户外导航,称为Htron。我们的主要思想是利用重尾政策参数化,这些参数隐含在稀疏的奖励环境中引起探索。我们在三种不同的室外场景中评估了针对钢琴,PPO和TRPO算法的htron的性能:进球,避免障碍和地形导航不均匀。我们平均观察到成功率的平均增加了34.41%,与其他方法相比,与其他方法获得的导航政策相比,为达到目标的平均时间步骤下降了15.15%,高程成本下降了24.9%。此外,我们证明我们的算法可以直接转移到Clearpath Husky机器人中,以在现实情况下进行户外地形导航。
translated by 谷歌翻译
Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement learning (RL) and the transformer-based models have manifested their potential in representative RL benchmarks. In this paper, we collect and dissect recent advances on transforming RL by transformer (transformer-based RL or TRL), in order to explore its development trajectory and future trend. We group existing developments in two categories: architecture enhancement and trajectory optimization, and examine the main applications of TRL in robotic manipulation, text-based games, navigation and autonomous driving. For architecture enhancement, these methods consider how to apply the powerful transformer structure to RL problems under the traditional RL framework, which model agents and environments much more precisely than deep RL methods, but they are still limited by the inherent defects of traditional RL algorithms, such as bootstrapping and "deadly triad". For trajectory optimization, these methods treat RL problems as sequence modeling and train a joint state-action model over entire trajectories under the behavior cloning framework, which are able to extract policies from static datasets and fully use the long-sequence modeling capability of the transformer. Given these advancements, extensions and challenges in TRL are reviewed and proposals about future direction are discussed. We hope that this survey can provide a detailed introduction to TRL and motivate future research in this rapidly developing field.
translated by 谷歌翻译
Underwater navigation presents several challenges, including unstructured unknown environments, lack of reliable localization systems (e.g., GPS), and poor visibility. Furthermore, good-quality obstacle detection sensors for underwater robots are scant and costly; and many sensors like RGB-D cameras and LiDAR only work in-air. To enable reliable mapless underwater navigation despite these challenges, we propose a low-cost end-to-end navigation system, based on a monocular camera and a fixed single-beam echo-sounder, that efficiently navigates an underwater robot to waypoints while avoiding nearby obstacles. Our proposed method is based on Proximal Policy Optimization (PPO), which takes as input current relative goal information, estimated depth images, echo-sounder readings, and previous executed actions, and outputs 3D robot actions in a normalized scale. End-to-end training was done in simulation, where we adopted domain randomization (varying underwater conditions and visibility) to learn a robust policy against noise and changes in visibility conditions. The experiments in simulation and real-world demonstrated that our proposed method is successful and resilient in navigating a low-cost underwater robot in unknown underwater environments. The implementation is made publicly available at https://github.com/dartmouthrobotics/deeprl-uw-robot-navigation.
translated by 谷歌翻译
在动态人类环境中,机器人安全,以社会符合社会的方式移动是长期机器人自主权的必要基准。但是,完全在现实世界中学习和基准基准社会导航行为是不可行的,因为学习是数据密集型的,并且在培训期间提供安全保证是一项挑战。因此,需要基于仿真的基准测试,这些基准需要为社会导航提供抽象。这些基准测试的框架将需要支持各种各样的学习方法,对广泛的社会导航情景可扩展,并抽象出感知问题,以明确关注社会导航。尽管有许多提出的解决方案,包括高保真3D模拟器和网格世界近似,但现有的解决方案尚未满足上述所有用于学习和评估社会导航行为的属性。在这项工作中,我们提出了SocialGym,这是一个轻巧的2D模拟环境,用于机器人社交导航,并考虑到可扩展性,以及基于SocialGym的基准场景。此外,我们提出了基准结果,将人类工程和基于模型的学习方法比较和对比,以从演示(LFD)(LFD)和增强学习(RL)方法(RL)方法(适用于社交机器人导航)进行了构想。这些结果证明了评估的每项政策的数据效率,任务绩效,社会合规性和环境转移能力,以为未来的社会导航研究提供扎实的基础。
translated by 谷歌翻译
我们提出了一种新颖的户外导航算法,以生成稳定,有效的动作,以将机器人导航到目标。我们使用多阶段的训练管道,并表明我们的模型产生了政策,从而在复杂的地形上导致稳定且可靠的机器人导航。基于近端政策优化(PPO)算法,我们开发了一种新颖的方法来实现户外导航任务的多种功能,即:减轻机器人的漂移,使机器人在颠簸的地形上保持稳定,避免在山丘上攀登,并具有陡峭的山坡,并改变了山坡,并保持了陡峭的高度变化,并使机器人稳定在山坡上,并避免了攀岩地面上的攀登,并避免了机器人的攀岩地形,并避免了机器人的攀岩地形。避免碰撞。我们的培训过程通过引入更广泛的环境和机器人参数以及统一模拟器中LIDAR感知的丰富特征来减轻现实(SIM到现实)差距。我们使用Clearphith Husky和Jackal在模拟和现实世界中评估我们的方法。此外,我们将我们的方法与最先进的方法进行了比较,并表明在现实世界中,它在不平坦的地形上至少提高了30.7%通过防止机器人在高梯度的区域移动,机器人在每个运动步骤处的高程变化。
translated by 谷歌翻译
在本文中,我们研究了DRL算法在本地导航问题的应用,其中机器人仅配备有限​​量距离的外部感受传感器(例如LIDAR),在未知和混乱的工作区中朝着目标位置移动。基于DRL的碰撞避免政策具有一些优势,但是一旦他们学习合适的动作的能力仅限于传感器范围,它们就非常容易受到本地最小值的影响。由于大多数机器人在非结构化环境中执行任务,因此寻求能够避免本地最小值的广义本地导航政策,尤其是在未经训练的情况下,这是非常兴趣的。为此,我们提出了一种新颖的奖励功能,该功能结合了在训练阶段获得的地图信息,从而提高了代理商故意最佳行动方案的能力。另外,我们使用SAC算法来训练我们的ANN,这表明在最先进的文献中比其他人更有效。一组SIM到SIM和SIM到现实的实验表明,我们提出的奖励与SAC相结合的表现优于比较局部最小值和避免碰撞的方法。
translated by 谷歌翻译
通过直接将感知输入映射到机器人控制命令中,深入的强化学习(DRL)算法已被证明在机器人导航中有效,尤其是在未知环境中。但是,大多数现有方法忽略导航中的局部最小问题,从而无法处理复杂的未知环境。在本文中,我们提出了第一个基于DRL的导航方法,该方法由具有连续动作空间,自适应向前模拟时间(AFST)的SMDP建模,以克服此问题。具体而言,我们通过修改其GAE来更好地估计SMDP中的策略梯度,改善了指定SMDP问题的分布式近端策略优化(DPPO)算法。我们在模拟器和现实世界中评估了我们的方法。
translated by 谷歌翻译
为了基于深度加强学习(RL)来增强目标驱动的视觉导航的交叉目标和跨场景,我们将信息理论正则化术语引入RL目标。正则化最大化导航动作与代理的视觉观察变换之间的互信息,从而促进更明智的导航决策。这样,代理通过学习变分生成模型来模拟动作观察动态。基于该模型,代理生成(想象)从其当前观察和导航目标的下一次观察。这样,代理学会了解导航操作与其观察变化之间的因果关系,这允许代理通过比较当前和想象的下一个观察来预测导航的下一个动作。 AI2-Thor框架上的交叉目标和跨场景评估表明,我们的方法在某些最先进的模型上获得了平均成功率的10美元。我们进一步评估了我们的模型在两个现实世界中:来自离散的活动视觉数据集(AVD)和带有TurtleBot的连续现实世界环境中的看不见的室内场景导航。我们证明我们的导航模型能够成功实现导航任务这些情景。视频和型号可以在补充材料中找到。
translated by 谷歌翻译
Robot navigation in dynamic environments shared with humans is an important but challenging task, which suffers from performance deterioration as the crowd grows. In this paper, multi-subgoal robot navigation approach based on deep reinforcement learning is proposed, which can reason about more comprehensive relationships among all agents (robot and humans). Specifically, the next position point is planned for the robot by introducing history information and interactions in our work. Firstly, based on subgraph network, the history information of all agents is aggregated before encoding interactions through a graph neural network, so as to improve the ability of the robot to anticipate the future scenarios implicitly. Further consideration, in order to reduce the probability of unreliable next position points, the selection module is designed after policy network in the reinforcement learning framework. In addition, the next position point generated from the selection module satisfied the task requirements better than that obtained directly from the policy network. The experiments demonstrate that our approach outperforms state-of-the-art approaches in terms of both success rate and collision rate, especially in crowded human environments.
translated by 谷歌翻译
为多个机器人制定安全,稳定和高效的避免障碍政策是具有挑战性的。大多数现有研究要么使用集中控制,要么需要与其他机器人进行通信。在本文中,我们提出了一种基于对数地图的新型对数深度强化学习方法,以避免复杂且无通信的多机器人方案。特别是,我们的方法将激光信息转换为对数图。为了提高训练速度和概括性能,我们的政策将在两个专门设计的多机器人方案中进行培训。与其他方法相比,对数图可以更准确地表示障碍,并提高避免障碍的成功率。我们最终在各种模拟和现实情况下评估了我们的方法。结果表明,我们的方法为复杂的多机器人场景和行人场景中的机器人提供了一种更稳定,更有效的导航解决方案。视频可在https://youtu.be/r0esuxe6mze上找到。
translated by 谷歌翻译
在狭窄的空间中,基于传统层次自治系统的运动计划可能会导致映射,定位和控制噪声引起碰撞。此外,当无映射时,它将被禁用。为了解决这些问题,我们利用深厚的加强学习,可以证明可以有效地进行自我决策,从而在狭窄的空间中自探索而无需地图,同时避免碰撞。具体而言,基于我们的Ackermann-Steering矩形Zebrat机器人及其凉亭模拟器,我们建议矩形安全区域来表示状态并检测矩形形状的机器人的碰撞,以及无需精心制作的奖励功能,不需要增强功能。目的地信息。然后,我们在模拟的狭窄轨道中基准了五种增强学习算法,包括DDPG,DQN,SAC,PPO和PPO-DISCRETE。经过训练,良好的DDPG和DQN型号可以转移到三个全新的模拟轨道上,然后转移到三个现实世界中。
translated by 谷歌翻译
主动同时定位和映射(SLAM)是规划和控制机器人运动以构建周围环境中最准确,最完整的模型的问题。自从三十多年前出现了积极感知的第一项基础工作以来,该领域在不同科学社区中受到了越来越多的关注。这带来了许多不同的方法和表述,并回顾了当前趋势,对于新的和经验丰富的研究人员来说都是非常有价值的。在这项工作中,我们在主动大满贯中调查了最先进的工作,并深入研究了仍然需要注意的公开挑战以满足现代应用程序的需求。为了实现现实世界的部署。在提供了历史观点之后,我们提出了一个统一的问题制定并审查经典解决方案方案,该方案将问题分解为三个阶段,以识别,选择和执行潜在的导航措施。然后,我们分析替代方法,包括基于深入强化学习的信念空间规划和现代技术,以及审查有关多机器人协调的相关工作。该手稿以讨论新的研究方向的讨论,解决可再现的研究,主动的空间感知和实际应用,以及其他主题。
translated by 谷歌翻译