Complex and contact-rich robotic manipulation tasks, particularly those that involve multi-fingered hands and underactuated object manipulation, present a significant challenge to any control method. Methods based on reinforcement learning offer an appealing choice for such settings, as they can enable robots to learn to delicately balance contact forces and dexterously reposition objects without strong modeling assumptions. However, running reinforcement learning on real-world dexterous manipulation systems often requires significant manual engineering. This negates the benefits of autonomous data collection and ease of use that reinforcement learning should in principle provide. In this paper, we describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks and enable robots with complex multi-fingered hands to learn to perform them through interaction. The core principle underlying our system is that, in a vision-based setting, users should be able to provide high-level intermediate supervision that circumvents challenges in teleoperation or kinesthetic teaching which allow a robot to not only learn a task efficiently but also to autonomously practice. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples, a reinforcement learning procedure that learns the task autonomously without interventions, and experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world, without simulation, manual modeling, or reward engineering.
translated by 谷歌翻译
强化学习(RL)算法有望为机器人系统实现自主技能获取。但是,实际上,现实世界中的机器人RL通常需要耗时的数据收集和频繁的人类干预来重置环境。此外,当部署超出知识的设置超出其学习的设置时,使用RL学到的机器人政策通常会失败。在这项工作中,我们研究了如何通过从先前看到的任务中收集的各种离线数据集的有效利用来应对这些挑战。当面对一项新任务时,我们的系统会适应以前学习的技能,以快速学习执行新任务并将环境返回到初始状态,从而有效地执行自己的环境重置。我们的经验结果表明,将先前的数据纳入机器人增强学习中可以实现自主学习,从而大大提高了学习的样本效率,并可以更好地概括。
translated by 谷歌翻译
我们研究机器人如何自主学习需要联合导航和抓握的技能。虽然原则上的加固学习提供自动机器人技能学习,但在实践中,在现实世界中的加固学习是挑战性的,并且往往需要大量的仪器和监督。我们的宗旨是以无论没有人为干预的自主方式,设计用于学习导航和操纵的机器人强化学习系统,在没有人为干预的情况下,在现实的假设下实现持续学习。我们建议的系统relmm,可以在没有任何环境仪器的现实世界平台上不断学习,没有人为干预,而无需访问特权信息,例如地图,对象位置或环境的全局视图。我们的方法采用模块化策略与组件进行操纵和导航,其中操纵政策不确定性驱动导航控制器的探索,操作模块为导航提供奖励。我们在房间清理任务上评估我们的方法,机器人必须导航到并拾取散落在地板上的物品。在掌握课程训练阶段之后,relmm可以在自动真实培训的大约40小时内自动学习导航并完全抓住。
translated by 谷歌翻译
加强学习(RL)提供了通过试验和错误学习的自然主义框架,这是由于其简单和有效性,并且由于其与人类和动物如何通过经验获得技能。然而,现实世界的体现学习,例如由人类和动物执行的,位于持续的非剧目世界中,而RL中的共同基准任务是epiSodic,在试验之间重置的环境以提供多次尝试。当尝试采取为ePiSodic模拟环境开发的RL算法并在现实世界平台上运行时,这种差异呈现出一项重大挑战,如机器人。在本文中,我们的目标是通过为自主强化学习(ARL)框架(ARL)提供框架来解决这一差异:加强学习的代理商不仅通过自己的经验学习,而且还争夺缺乏人类监督在试验之间重置。我们在此框架上介绍了一个模拟的基准伯爵,其中包含一系列多样化和具有挑战性的模拟任务,这些任务反映了所引入学习的障碍,当只有最小的对外在干预的依赖性时,可以假设。我们表明,作为干预措施的剧集RL和现有方法斗争的标准方法最小化,强调了对强化学习开发新算法的需求,更加注重自主。
translated by 谷歌翻译
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algorithm that acquires such general-purpose skills by combining unsupervised representation learning and reinforcement learning of goal-conditioned policies. Since the particular goals that might be required at test-time are not known in advance, the agent performs a self-supervised "practice" phase where it imagines goals and attempts to achieve them. We learn a visual representation with three distinct purposes: sampling goals for self-supervised practice, providing a structured transformation of raw sensory inputs, and computing a reward signal for goal reaching. We also propose a retroactive goal relabeling scheme to further improve the sample-efficiency of our method. Our off-policy algorithm is efficient enough to learn policies that operate on raw image observations and goals for a real-world robotic system, and substantially outperforms prior techniques. * Equal contribution. Order was determined by coin flip.
translated by 谷歌翻译
Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on offpolicy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.
translated by 谷歌翻译
现实的操纵任务要求机器人与具有长时间运动动作序列的环境相互作用。尽管最近出现了深厚的强化学习方法,这是自动化操作行为的有希望的范式,但由于勘探负担,它们通常在长途任务中缺乏。这项工作介绍了操纵原始增强的强化学习(Maple),这是一个学习框架,可通过预定的行为原始库来增强标准强化学习算法。这些行为原始素是专门实现操纵目标(例如抓住和推动)的强大功能模块。为了使用这些异质原始素,我们制定了涉及原语的层次结构策略,并使用输入参数实例化执行。我们证明,枫树的表现优于基线方法,通过一系列模拟的操纵任务的大幅度。我们还量化了学习行为的组成结构,并突出了我们方法将策略转移到新任务变体和物理硬件的能力。视频和代码可从https://ut-aut-autin-rpl.github.io/maple获得
translated by 谷歌翻译
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Our method, which builds on top of Deep Deterministic Policy Gradients and Hindsight Experience Replay, provides an order of magnitude of speedup over RL on simulated robotics tasks. It is simple to implement and makes only the additional assumption that we can collect a small set of demonstrations. Furthermore, our method is able to solve tasks not solvable by either RL or behavior cloning alone, and often ends up outperforming the demonstrator policy.
translated by 谷歌翻译
在本文中,我们研究了可以从原始图像中学习低级技能的曲目的问题,这些曲目可以测序以完成长效的视觉运动任务。强化学习(RL)是一种自主获取短疗法技能的有前途的方法。但是,RL算法的重点很大程度上是这些个人技能的成功,而不是学习和扎根大量的技能曲目,这些技能可以对这些技能进行测序,这些技能可以对完成扩展的多阶段任务进行测序。后者需要稳健性和持久性,因为技能的错误会随着时间的流逝而复杂,并且可能要求机器人在其曲目中具有许多原始技能,而不仅仅是一个。为此,我们介绍了Ember,Ember是一种基于模型的RL方法,用于学习原始技能,适合完成长途视觉运动任务。 Ember使用学识渊博的模型,评论家和成功分类器学习和计划,成功分类器既可以作为RL的奖励功能,又是一种基础机制,可连续检测机器人在失败或扰动下是否应重试技能。此外,学到的模型是任务不合时宜的,并使用来自所有技能的数据进行了培训,从而使机器人能够有效地学习许多不同的原语。这些视觉运动原始技能及其相关的前后条件可以直接与现成的符号计划者结合在一起,以完成长途任务。在Franka Emika机器人部门上,我们发现Ember使机器人能够以85%的成功率完成三个长马视觉运动任务,例如组织办公桌,文件柜和抽屉,需要排序多达12个技能,这些技能最多需要12个技能,涉及14个独特的学识渊博,并要求对新物体进行概括。
translated by 谷歌翻译
我们研究了从机器人交互的大型离线数据集学习一系列基于视觉的操纵任务的问题。为了实现这一目标,人类需要简单有效地将任务指定给机器人。目标图像是一种流行的任务规范形式,因为它们已经在机器人的观察空间接地。然而,目标图像也有许多缺点:它们对人类提供的不方便,它们可以通过提供导致稀疏奖励信号的所需行为,或者在非目标达到任务的情况下指定任务信息。自然语言为任务规范提供了一种方便而灵活的替代方案,而是随着机器人观察空间的接地语言挑战。为了可扩展地学习此基础,我们建议利用具有人群源语言标签的离线机器人数据集(包括高度最佳,自主收集的数据)。使用此数据,我们学习一个简单的分类器,该分类器预测状态的更改是否完成了语言指令。这提供了一种语言调节奖励函数,然后可以用于离线多任务RL。在我们的实验中,我们发现,在语言条件的操作任务中,我们的方法优于目标 - 图像规格和语言条件仿制技术超过25%,并且能够从自然语言中执行Visuomotor任务,例如“打开右抽屉“和”移动订书机“,在弗兰卡·埃米卡熊猫机器人上。
translated by 谷歌翻译
Dexterous manipulation with anthropomorphic robot hands remains a challenging problem in robotics because of the high-dimensional state and action spaces and complex contacts. Nevertheless, skillful closed-loop manipulation is required to enable humanoid robots to operate in unstructured real-world environments. Reinforcement learning (RL) has traditionally imposed enormous interaction data requirements for optimizing such complex control problems. We introduce a new framework that leverages recent advances in GPU-based simulation along with the strength of imitation learning in guiding policy search towards promising behaviors to make RL training feasible in these domains. To this end, we present an immersive virtual reality teleoperation interface designed for interactive human-like manipulation on contact rich tasks and a suite of manipulation environments inspired by tasks of daily living. Finally, we demonstrate the complementary strengths of massively parallel RL and imitation learning, yielding robust and natural behaviors. Videos of trained policies, our source code, and the collected demonstration datasets are available at https://maltemosbach.github.io/interactive_ human_like_manipulation/.
translated by 谷歌翻译
Physical interactions can often help reveal information that is not readily apparent. For example, we may tug at a table leg to evaluate whether it is built well, or turn a water bottle upside down to check that it is watertight. We propose to train robots to acquire such interactive behaviors automatically, for the purpose of evaluating the result of an attempted robotic skill execution. These evaluations in turn serve as "interactive reward functions" (IRFs) for training reinforcement learning policies to perform the target skill, such as screwing the table leg tightly. In addition, even after task policies are fully trained, IRFs can serve as verification mechanisms that improve online task execution. For any given task, our IRFs can be conveniently trained using only examples of successful outcomes, and no further specification is needed to train the task policy thereafter. In our evaluations on door locking and weighted block stacking in simulation, and screw tightening on a real robot, IRFs enable large performance improvements, even outperforming baselines with access to demonstrations or carefully engineered rewards. Project website: https://sites.google.com/view/lirf-corl-2022/
translated by 谷歌翻译
While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and policy exploitation. Preference based RL algorithms seek to overcome these challenges by directly learning reward functions from human feedback. Unfortunately, prior work either requires an unreasonable number of queries implausible for any human to answer or overly restricts the class of reward functions to guarantee the elicitation of the most informative queries, resulting in models that are insufficiently expressive for realistic robotics tasks. Contrary to most works that focus on query selection to \emph{minimize} the amount of data required for learning reward functions, we take an opposite approach: \emph{expanding} the pool of available data by viewing human-in-the-loop RL through the more flexible lens of multi-task learning. Motivated by the success of meta-learning, we pre-train preference models on prior task data and quickly adapt them for new tasks using only a handful of queries. Empirically, we reduce the amount of online feedback needed to train manipulation policies in Meta-World by 20$\times$, and demonstrate the effectiveness of our method on a real Franka Panda Robot. Moreover, this reduction in query-complexity allows us to train robot policies from actual human users. Videos of our results and code can be found at https://sites.google.com/view/few-shot-preference-rl/home.
translated by 谷歌翻译
无监督的表示学习的最新进展显着提高了模拟环境中培训强化学习政策的样本效率。但是,尚未看到针对实体强化学习的类似收益。在这项工作中,我们专注于从像素中启用数据有效的实体机器人学习。我们提出了有效的机器人学习(编码器)的对比前训练和数据增强,该方法利用数据增强和无监督的学习来从稀疏奖励中实现对实体ARM策略的样本效率培训。虽然对比预训练,数据增强,演示和强化学习不足以进行有效学习,但我们的主要贡献表明,这些不同技术的组合导致了一种简单而数据效率的方法。我们表明,只有10个示范,一个机器人手臂可以从像素中学习稀疏的奖励操纵策略,例如到达,拾取,移动,拉动大物体,翻转开关并在短短30分钟内打开抽屉现实世界训练时间。我们在项目网站上包括视频和代码:https://sites.google.com/view/felfficited-robotic-manipulation/home
translated by 谷歌翻译
在现实世界中,教授多指的灵巧机器人在现实世界中掌握物体,这是一个充满挑战的问题,由于其高维状态和动作空间。我们提出了一个机器人学习系统,该系统可以进行少量的人类示范,并学会掌握在某些被遮挡的观察结果的情况下掌握看不见的物体姿势。我们的系统利用了一个小型运动捕获数据集,并为多指的机器人抓手生成具有多种多样且成功的轨迹的大型数据集。通过添加域随机化,我们表明我们的数据集提供了可以将其转移到策略学习者的强大抓地力轨迹。我们训练一种灵活的抓紧策略,该策略将对象的点云作为输入,并预测连续的动作以从不同初始机器人状态掌握对象。我们在模拟中评估了系统对22多伏的浮动手的有效性,并在现实世界中带有kuka手臂的23多杆Allegro机器人手。从我们的数据集中汲取的政策可以很好地概括在模拟和现实世界中的看不见的对象姿势
translated by 谷歌翻译
通过各种物体学习各种灵巧的操纵行为仍然是一个开放的巨大挑战。虽然政策学习方法为攻击此问题提供了强大的途径,但它们需要大量的每任务工程和算法调整。本文试图通过开发预先保证的灵巧操纵(PGDM)框架来逃避这些约束,从而在没有任何特定于任务的推理或超级参数调整的情况下会产生各种灵活的操纵行为。 PGD​​M的核心是一种众所周知的机器人构建体,即pre grasps(即用于对象相互作用的手工置序)。这种简单的原始性足以诱导有效的探索策略来获取复杂的灵巧操纵行为。为了详尽地验证这些主张,我们介绍了TCDM,这是根据多个对象和灵巧的操纵器定义的50个不同操纵任务的基准。 TCDM的任务是使用来自各种来源(动画师,人类行为等)的示例对象轨迹自动定义的,而无需任何执行任务工程和/或监督。我们的实验验证了PGDM的探索策略,该策略是由令人惊讶的简单成分(单个预抓姿势)引起的,与先前方法的性能相匹配,这些方法需要昂贵的每任意功能/奖励工程,专家监督和高参数调整。有关动画可视化,训练有素的策略和项目代码,请参阅:https://pregrasps.github.io/
translated by 谷歌翻译
我们研究了复杂几何物体的机器人堆叠问题。我们提出了一个挑战和多样化的这些物体,这些物体被精心设计,以便要求超出简单的“拾取”解决方案之外的策略。我们的方法是加强学习(RL)方法与基于视觉的互动政策蒸馏和模拟到现实转移相结合。我们的学习政策可以有效地处理现实世界中的多个对象组合,并展示各种各样的堆叠技能。在一个大型的实验研究中,我们调查在模拟中学习这种基于视觉的基于视觉的代理的选择,以及对真实机器人的最佳转移产生了什么影响。然后,我们利用这些策略收集的数据并通过离线RL改善它们。我们工作的视频和博客文章作为补充材料提供。
translated by 谷歌翻译
非结构化环境中的多步操纵任务对于学习的机器人来说非常具有挑战性。这些任务相互作用,包括可以获得的预期状态,可以实现整体任务和低级推理,以确定哪些行动将产生这些国家。我们提出了一种无模型的深度加强学习方法来学习多步理操作任务。我们介绍了一个基于视觉的模型架构的机器人操纵网络(ROMANNET),以了解动作值函数并预测操纵操作候选。我们定义基于Gaussian(TPG)奖励函数的任务进度,基于导致成功的动作原语的行动和实现整体任务目标的进展来计算奖励。为了平衡探索/剥削的比率,我们介绍了一个损失调整后的探索(LAE)政策,根据亏损估计的Boltzmann分配来确定来自行动候选人的行动。我们通过培训ROMANNET来展示我们方法的有效性,以了解模拟和现实世界中的几个挑战的多步机械管理任务。实验结果表明,我们的方法优于现有的方法,并在成功率和行动效率方面实现了最先进的性能。消融研究表明,TPG和LAE对多个块堆叠的任务特别有益。代码可用:https://github.com/skumra/romannet
translated by 谷歌翻译
连续控制设置中的复杂顺序任务通常需要代理在其状态空间中成功遍历一组“窄段”。通过以样本有效的方式解决具有稀疏奖励的这些任务对现代钢筋(RL)构成了挑战,由于问题的相关的长地平性,并且在学习期间缺乏充足的正信号。已应用各种工具来解决这一挑战。当可用时,大型演示可以指导代理探索。后威尔同时释放不需要额外的信息来源。然而,现有的战略基于任务不可行的目标分布探索,这可以使长地平线的解决方案不切实际。在这项工作中,我们扩展了后视可释放的机制,以指导沿着一小组成功示范所暗示的特定任务特定分布的探索。我们评估了四个复杂,单身和双臂,机器人操纵任务的方法,对抗强合适的基线。该方法需要较少的演示来解决所有任务,并且达到明显更高的整体性能作为任务复杂性增加。最后,我们研究了提出的解决方案对输入表示质量和示范人数的鲁棒性。
translated by 谷歌翻译
从意外的外部扰动中恢复的能力是双模型运动的基本机动技能。有效的答复包括不仅可以恢复平衡并保持稳定性的能力,而且在平衡恢复物质不可行时,也可以保证安全的方式。对于与双式运动有关的机器人,例如人形机器人和辅助机器人设备,可帮助人类行走,设计能够提供这种稳定性和安全性的控制器可以防止机器人损坏或防止伤害相关的医疗费用。这是一个具有挑战性的任务,因为它涉及用触点产生高维,非线性和致动系统的高动态运动。尽管使用基于模型和优化方法的前进方面,但诸如广泛领域知识的要求,诸如较大的计算时间和有限的动态变化的鲁棒性仍然会使这个打开问题。在本文中,为了解决这些问题,我们开发基于学习的算法,能够为两种不同的机器人合成推送恢复控制政策:人形机器人和有助于双模型运动的辅助机器人设备。我们的工作可以分为两个密切相关的指示:1)学习人形机器人的安全下降和预防策略,2)使用机器人辅助装置学习人类的预防策略。为实现这一目标,我们介绍了一套深度加强学习(DRL)算法,以学习使用这些机器人时提高安全性的控制策略。
translated by 谷歌翻译