A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a challenging problem, particularly when hand-engineered reward functions are not available. Learned dynamics models are a promising approach for learning about the environment without rewards or task-directed data, but planning to reach goals with such a model requires a notion of functional similarity between observations and goal states. We present a self-supervised method for model-based visual goal reaching, which uses both a visual dynamics model as well as a dynamical distance function learned using model-free reinforcement learning. Our approach learns entirely using offline, unlabeled data, making it practical to scale to large and diverse datasets. In our experiments, we find that our method can successfully learn models that perform a variety of tasks at test-time, moving objects amid distractors with a simulated robotic arm and even learning to open and close a drawer using a real-world robot. In comparisons, we find that this approach substantially outperforms both model-free and model-based prior methods. Videos and visualizations are available here: http://sites.google.com/berkeley.edu/mbold.
University of Pennsylvania（宾夕法尼亚大学）；UC Berkeley（加州大学伯克利分校）；Google（谷歌）；Facebook AI Research（Facebook AI研究院）
Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both these challenges through a new approach to self-supervised exploration and fast adaptation to new tasks, which need not be known during exploration. During exploration, unlike prior methods which retrospectively compute the novelty of observations after the agent has already reached them, our agent acts efficiently by leveraging planning to seek out expected f…
Stanford University（斯坦福大学）；University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）
A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. We propose learning these through interacting with a visual and dynamic environment. Our proposed solution involves bootstr…
University of Eastern Finland（东芬兰大学）；Shenzhen Technology University（深圳技术大学）
We investigate and analyze principles of typical motion planning algorithms. These include traditional planning algorithms, supervised learning, optimal value reinforcement learning, policy gradient reinforcement learning. Traditional planning algorithms we investigated include graph search algorithms, sampling-based algorithms, and interpolating curve algorithms. Supervised learning algorithms include MSVM, LSTM, MCTS and CNN. Optimal value reinforcement learning algorithms include Q learning, DQN, double DQN, dueling DQN. Policy gradient algorithms include policy gradient method, actor-criti…
Institute of Robotics and Machine Intelligence（机器人与机器智能研究所）；Poznan University of Technology（波兹南理工大学）
An efficient path planner for autonomous car-like vehicles should handle the strong kinematic constraints, particularly in confined spaces commonly encountered while maneuvering in city traffic, and should enable rapid planning, as the city traffic scenarios are highly dynamic. State-of-the-art planning algorithms handle such difficult cases at high computational cost, often yielding non-deterministic results. However, feasible local paths can be quickly generated leveraging the past planning experience gained in the same or similar environment. While learning through supervised training is pr…
UC Berkeley（加州大学伯克利分校）；Technical University of Munich（慕尼黑工业大学）
In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected data is prediction: if a robot can learn to predict the future, it can use this predictive model to take actions to produce desired outcomes, such as moving an object to a particular location. However, in complex open-world scenarios, designing a representation for prediction is difficult. In this work, we instead aim to enable self-supervised robotic learnin…
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院（BIGAI））；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Yuanpei College, Peking University（北京大学元培学院）；University of California, Los Angeles (UCLA)（加利福尼亚大学洛杉矶分校）
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space which follow trajectories caused by vehicle control actions to enhance predictive accuracy during planning. The attention model is jointly optimized by the task-specific loss and an additional trajectory-constraint loss, allowing adaptability yet encouraging a regularized structure for improved generalization and reliability. Importantly, visual attention i…
Towards Bio-Inspired Robotic Trajectory Planning via Self-Supervised RNN
Faculty of Mathematics, Physics and Informatics, Comenius University Bratislava（数学、物理与信息学系，科门尼乌斯大学布拉迪斯拉发分校）；Department of Informatics, University of Hamburg（信息学系，汉堡大学）
Berkeley AI Research, University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究）；Technion（以色列理工学院（Technion））
In visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e.g., images obtained from self-supervised robot interaction. Most previous works on VP approached the problem by planning in a learned latent space, resulting in low-quality visual plans, and difficult training algorithms. Here, instead, we propose a simple VP method that plans directly in image space and displays competitive performance. We build on the semi-parametric topological memory (SPTM) method: image samples are treated as nodes in a graph, the graph conne…
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor scalability of sampling-based planning optimizers, one significant limitation of these approaches is the ability to plan over long horizons to reach distant goals. To that end, we propose a framework for subgoal generation and planning, hierarchical visual foresight (HVF), which g…
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and then gradually filling in details. In contrast, current learning approaches for visual prediction and planning fail on long-horizon tasks as they generate predictions (1) without considering goal information, and (2) at the finest temporal resolution, one step at a time. In this work we propose a framework for visual prediction and planning that is able to overcome both of these …
Sun Yat-sen University（中山大学）；Guangdong Polytechnic Normal University（广东技术师范大学）
There has been increasing attention on planning model learning in classical planning. Most existing approaches, however, focus on learning planning models from structured data in symbolic representations. It is often difficult to obtain such structured data in real-world scenarios. Although a number of approaches have been developed for learning planning models from fully observed unstructured data (e.g., images), in many scenarios raw observations are often incomplete. In this paper, we provide a novel framework, \aType{Recplan}, for learning a transition model from partially observed raw ima…
Information planning enables faster learning with fewer training examples. It is particularly applicable when training examples are costly to obtain. This work examines the advantages of information planning for text data by focusing on three supervised models: Naive Bayes, supervised LDA and deep neural networks. We show that planning based on entropy and mutual information outperforms random selection baseline and therefore accelerates learning.
In this paper, we introduce a novel framework that can learn to make visual predictions about the motion of a robotic agent from raw video frames. Our proposed motion prediction network (PROM-Net) can learn in a completely unsupervised manner and efficiently predict up to 10 frames in the future. Moreover, unlike any other motion prediction models, it is lightweight and once trained it can be easily implemented on mobile platforms that have very limited computing capabilities. We have created a new robotic data set comprising LEGO Mindstorms moving along various trajectories in three different…
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents is not well understood because existing work has focused on model-free agents when benchmarking generalization. Here, we explicitly measure the generalization ability of model-based agents in comparison to their model-free counterparts. We focus our analysis on MuZero (Schrittwieser et al., 2020), a powerful model-based agent, and evaluate its performance on …
KTH Royal Institute of Technology（瑞典皇家理工学院）；University of Salerno（萨莱诺大学）；University of Cassino and Southern Lazio（卡西诺大学和南拉齐奥大学）
We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects. Planning is performed in a low-dimensional latent state space that embeds images. We define and implement a Latent Space Roadmap (LSR) which is a graph-based structure that globally captures the latent system dynamics. Our framework consists of two main components: a Visual Foresight Module (VFM) that generates a visual plan as a sequence of images, and an Action Proposal Network (APN) that predicts the actions between them. We show the …
Planning for robotic manipulation requires reasoning about the changes a robot can affect on objects. When such interactions can be modelled analytically, as in domains with rigid objects, efficient planning algorithms exist. However, in both domestic and industrial domains, the objects of interest can be soft, or deformable, and hard to model analytically. For such cases, we posit that a data-driven modelling approach is more suitable. In recent years, progress in deep generative models has produced methods that learn to `imagine' plausible images from data. Building on the recent Causal Info…
University of Stuttgart（斯图加特大学）；Max-Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；TU Berlin（柏林工业大学）
In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimization. Due to the great combinatorial complexity of possible discrete action sequences, a large number of optimization/motion planning problems have to be solved to find a solution, which limits the scalability of these approaches. To circumvent thi…
Warsaw University of Technology（华沙理工大学）；Jagiellonian University（雅盖隆大学）；Institute of Applied Psychology（应用心理学研究所）
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind. Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language i…
Reliably planning fingertip grasps for multi-fingered hands lies as a key challenge for many tasks including tool use, insertion, and dexterous in-hand manipulation. This task becomes even more difficult when the robot lacks an accurate model of the object to be grasped. Tactile sensing offers a promising approach to account for uncertainties in object shape. However, current robotic hands tend to lack full tactile coverage. As such, a problem arises of how to plan and execute grasps for multi-fingered hands such that contact is made with the area covered by the tactile sensors. To address thi…
University of Torontoland（多伦托兰大学）；Googol ShallowMind（古戈尔浅智公司）；University of Edenborrow（伊登伯罗大学）
Learning state representations enables robotic planning directly from raw observations such as images. Most methods learn state representations by utilizing losses based on the reconstruction of the raw observations from a lower-dimensional latent space. The similarity between observations in the space of images is often assumed and used as a proxy for estimating similarity between the underlying states of the system. However, observations commonly contain task-irrelevant factors of variation which are nonetheless important for reconstruction, such as varying lighting and different camera view…
KTH Royal Institute of Technology（KTH皇家理工学院）；Roma Tre University（罗马第三大学）；University of Cassino and Southern Lazio（卡西诺和南拉齐奥大学）
We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects. We propose a Latent Space Roadmap (LSR) for task planning which is a graph-based structure globally capturing the system dynamics in a low-dimensional latent space. Our framework consists of three parts: (1) a Mapping Module (MM) that maps observations given in the form of images into a structured latent space extracting the respective states as well as generates observations from the latent states, (2) the LSR which builds and conn…
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection resul…
We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI). We consider the implicit hierarchy present in the videos and make use of (i) frame-level invariances (e.g. stability to color and contrast perturbations), (ii) shot/clip-level invariances (e.g. robustness to changes in object orientation and lighting conditions), and (iii) video-level invariances (semantic relationships of scenes across shots/clips), to define a holistic self-supervised loss. Training models using different variants of the propose…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；United States Army Research Laboratory (ARL)（美国陆军研究实验室）
Autonomous mobile robots deployed in outdoor environments must reason about different types of terrain for both safety (e.g., prefer dirt over mud) and deployer preferences (e.g., prefer dirt path over flower beds). Most existing solutions to this preference-aware path planning problem use semantic segmentation to classify terrain types from camera images, and then ascribe costs to each type. Unfortunately, there are three key limitations of such approaches -- they 1) require pre-enumeration of the discrete terrain types, 2) are unable to handle hybrid terrain types (e.g., grassy dirt), and 3)…
Indian Institute of Technology, Gandhinagar（甘地讷格尔印度理工学院）
We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human annotation. To avoid the cost of labeling data, self-supervised methods were proposed to make use of largely available unlabeled data. This study conducts a comprehensive and insightful survey and analysis of recent developments in the self-supervised paradigm for feature representation. In this paper, we investigate the factors affecting the usefulness of se…
Mila – Quebec AI Institute（Mila-魁北克人工智能研究所）；McGill University（麦吉尔大学）；Facebook AI Research（Facebook人工智能研究院）；University of Montreal（蒙特利尔大学）
We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on noise-contrastive estimation and neighbourhood component analysis, that aims to distinguish examples of different classes in addition to the self-supervised instance-wise pretext tasks. On ImageNet, we find that SuNCEt can be used to match the semi-supervised learning accuracy of previous contrastive approaches while using less than half the amount of pre-training …
University of Adelaide（阿德莱德大学）；Amazon（亚马逊）；Idiap Research Institute（Idiap研究所）
The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vision-and-language models has shown that self-supervised learning is effective for pretraining multimodal interactions. In this technical report, we focus on visual representations. We review and evaluate self-supervised methods to leverage unlabeled images and pretrain a model, which we then fine-tune on a custom VQA task that allows controlled evaluation and diagnosis. We compare energy-based models (EBMs) with cont…
Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所台湾国际研究生计划社交网络与人本计算项目）；Department of Computer Science, National Chengchi University（国立政治大学资讯科学系）；Institute of Information Systems and Applications, National Tsing Hua University（国立清华大学资讯系统与应用研究所）；National Institute of Informatics（国立情报学研究所）；Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University（国立清华大学电机工程学系与通讯工程研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of neural representations, we explore in this direction by comparing a contrastive self-supervised algorithm to supervision for simple image data in a common architecture. We find that the methods learn similar intermediate representations through dissimilar means, and that the representations diverge rapidly in the final few layers. We investigate this divergence…
Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly detection. While classification, object detection, and segmentation have been investigated with self-supervised learning, anomaly detection needs more attention. We consider the problem of anomaly detection in images and videos, and present a new visual anomaly detection technique for videos. Numerous seminal and state-of-the-art self-supervised methods are evaluated…
Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervis…
