We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, which limits the scalability of the approaches. Our main contribution is to formulate one-shot imitation learning as a symbolic planning problem along with the symbol grounding problem. This formulation disentangles the policy execution from the inter-task generalization and leads to better data efficiency. The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures. We address this challenge by proposing a continuous relaxation of the discrete symbolic planner that directly plans on the probabilistic outputs of the symbol grounding model. Our continuous relaxation of the planner can still leverage the information contained in the probabilistic symbol grounding and significantly improve over the baseline planner for the one-shot imitation learning tasks without using large training data.
Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
Intelligent Autonomous Systems, TU Darmstadt, Germany（图腾达姆施塔特大学智能自主系统研究所）；German Research Center for AI, Germany（德国人工智能研究中心）；Hessian Centre for Artificial Intelligence, Germany（黑森州人工智能中心）；Honda Research Institute EU, Germany（本田欧洲研究院）
Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies
Department of Science and Engineering, the George Washington University（科学与工程系，乔治·华盛顿大学）；Autonomous Vehicles Lab, Department of Mechanical Engineering, University of Surrey（自主车辆实验室，机械工程系，萨里大学）
Translating Flow to Policy via Hindsight Online Imitation
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；University of California San Diego（加州大学圣地亚哥分校）；Washington University in St. Louis（圣路易斯华盛顿大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Qi Zhi Institute（上海启智研究所）
Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight
Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院 Cyber-系统与控制研究所）；Huzhou Institute, Zhejiang University（浙江大学湖州研究院）；Institute of Systems Engineering, China Academy of Engineering Physics（中国工程物理研究院系统工程研究所）；School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）；Department of Automation, North China Electric Power University (Baoding)（华北电力大学（保定）自动化系）；Differential Robotics Technology Company（差分机器人技术公司）
Sequences and time-series often arise in robot tasks, e.g., in activity recognition and imitation learning. In recent years, deep neural networks (DNNs) have emerged as an effective data-driven methodology for processing sequences given sufficient training data and compute resources. However, when data is limited, simpler models such as logic/rule-based methods work surprisingly well, especially when relevant prior knowledge is applied in their construction. However, unlike DNNs, these "structured" models can be difficult to extend, and do not work well with raw unstructured data. In this work…
We investigate what grade of sensor data is required for training an imitation-learning-based AV planner on human expert demonstration. Machine-learned planners are very hungry for training data, which is usually collected using vehicles equipped with the same sensors used for autonomous operation. This is costly and non-scalable. If cheaper sensors could be used for collection instead, data availability would go up, which is crucial in a field where data volume requirements are large and availability is small. We present experiments using up to 1000 hours worth of expert demonstration and fin…
We present a learning-based planner that aims to robustly drive a vehicle by mimicking human drivers' driving behavior. We leverage a mid-to-mid approach that allows us to manipulate the input to our imitation learning network freely. With that in mind, we propose a novel feedback synthesizer for data augmentation. It allows our agent to gain more driving experience in various previously unseen environments that are likely to encounter, thus improving overall performance. This is in contrast to prior works that rely purely on random synthesizers. Furthermore, rather than completely commit to i…
Carnegie Mellon University（卡内基梅隆大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO））；University of Southern California（南加州大学）
Multi-agent path finding (MAPF) is an essential component of many large-scale, real-world robot deployments, from aerial swarms to warehouse automation. However, despite the community's continued efforts, most state-of-the-art MAPF planners still rely on centralized planning and scale poorly past a few hundred agents. Such planning approaches are maladapted to real-world deployments, where noise and uncertainty often require paths be recomputed online, which is impossible when planning times are in seconds to minutes. We present PRIMAL, a novel framework for MAPF that combines reinforcement an…
Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a challenging problem in deploying IL and RL methods is how to generate and collect massive, broadly distributed data such that these methods can generalize effectively. In this work, we solve this problem using our proposed approach called {self-imitation learning by planning (SILP)}, where demonstration data are collected automatically by planning on the visited stat…
Carnegie Mellon University（卡内基梅隆大学）；School of Computer Science（计算机学院）；Robotics Institute（机器人研究所）
Planners using accurate models can be effective for accomplishing manipulation tasks in the real world, but are typically highly specialized and require significant fine-tuning to be reliable. Meanwhile, learning is useful for adaptation, but can require a substantial amount of data collection. In this paper, we propose a method that improves the efficiency of sub-optimal planners with approximate but simple and fast models by switching to a model-free policy when unexpected transitions are observed. Unlike previous work, our method specifically addresses when the planner fails due to transiti…
Five AI Ltd.（Five AI有限公司）；University of Oxford（牛津大学）；University of Edinburgh（爱丁堡大学）
Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing safe, smooth and comfortable plans, but often at the cost of runtime efficiency. On the other hand, naively deploying trajectories produced by efficient-to-run deep imitation learning approaches might risk compromising safety. In this paper, we present PILOT -- a planning framework that comprises an imitation neural network followed by an efficient optimiser that actively rectifies the network's plan, guaranteeing fu…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
This paper presents a vision-based modularized drone racing navigation system that uses a customized convolutional neural network (CNN) for the perception module to produce high-level navigation commands and then leverages a state-of-the-art planner and controller to generate low-level control commands, thus exploiting the advantages of both data-based and model-based approaches. Unlike the state-of-the-art method which only takes the current camera image as the CNN input, we further add the latest three drone states as part of the inputs. Our method outperforms the state-of-the-art method in …
The ability to perform effective planning is crucial for building an instruction-following agent. When navigating through a new environment, an agent is challenged with (1) connecting the natural language instructions with its progressively growing knowledge of the world; and (2) performing long-range planning and decision making in the form of effective exploration and error correction. Current methods are still limited on both fronts despite extensive efforts. In this paper, we introduce the Evolving Graphical Planner (EGP), a model that performs global planning for navigation based on raw s…
Georgia Institute of Technology（佐治亚理工学院）；University of Genova（热那亚大学）；Imperial College London（帝国理工学院）
A novel skill learning approach is proposed that allows a robot to acquire human-like visuospatial skills for object manipulation tasks. Visuospatial skills are attained by observing spatial relationships among objects through demonstrations. The proposed Visuospatial Skill Learning (VSL) is a goal-based approach that focuses on achieving a desired goal configuration of objects relative to one another while maintaining the sequence of operations. VSL is capable of learning and generalizing multi-operation skills from a single demonstration, while requiring minimum prior knowledge about the obj…
Dynamic quadruped locomotion over challenging terrains with precise foot placements is a hard problem for both optimal control methods and Reinforcement Learning (RL). Non-linear solvers can produce coordinated constraint satisfying motions, but often take too long to converge for online application. RL methods can learn dynamic reactive controllers but require carefully tuned shaping rewards to produce good gaits and can have trouble discovering precise coordinated movements. Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for …
Department of Aeronautics and Astronautics, Massachusetts Institute of Technology（航空与航天系，麻省理工学院）；Institute for Research in Technology, ICAI School of Engineering, Comillas Pontifical University (Spain)（技术研究所，ICAI工程学院，Comillas天主教大学（西班牙））
Rethinking Imitation-based Planner for Autonomous Driving
Hong Kong University of Science and Technology（香港科技大学）；Lotus Technology Ltd.（路特斯科技有限公司）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
The American University in Cairo（开罗美国大学）；Valeo Schalter und Sensoren GmbH（法雷奥开关与传感器有限公司）；Valeo Egypt（法雷奥埃及公司）
Conditional imitation learning (CIL) trains deep neural networks, in an end-to-end manner, to mimic human driving. This approach has demonstrated suitable vehicle control when following roads, avoiding obstacles, or taking specific turns at intersections to reach a destination. Unfortunately, performance dramatically decreases when deployed to unseen environments and is inconsistent against varying weather conditions. Most importantly, the current CIL fails to avoid static road blockages. In this work, we propose a solution to those deficiencies. First, we fuse the laser scanner with the regul…
We propose a learning-from-demonstration approach for grounding actions from expert data and an algorithm for using these actions to perform a task in new environments. Our approach is based on an application of sampling-based motion planning to search through the tree of discrete, high-level actions constructed from a symbolic representation of a task. Recursive sampling-based planning is used to explore the space of possible continuous-space instantiations of these actions. We demonstrate the utility of our approach with a magnetic structure assembly task, showing that the robot can intellig…
Stanford University（斯坦福大学）；NVIDIA（英伟达）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；University of Toronto（多伦多大学）；University of Washington（华盛顿大学）
We address goal-based imitation learning, where the aim is to output the symbolic goal from a third-person video demonstration. This enables the robot to plan for execution and reproduce the same goal in a completely different environment. The key challenge is that the goal of a video demonstration is often ambiguous at the level of semantic actions. The human demonstrators might unintentionally achieve certain subgoals in the demonstrations with their actions. Our main contribution is to propose a motion reasoning framework that combines task and motion planning to disambiguate the true inten…
Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs
University of Technology Sydney（悉尼科技大学）；Australia Artificial Intelligence Institute（澳大利亚人工智能研究院）；School of Computer Science（计算机学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（信息处理国家重点实验室，计算机学院，北京大学）；University of Washington（华盛顿大学）；Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心）
DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners
School of Vehicle and Mobility, Tsinghua University（车辆与移动系统学院，清华大学）；Dongfeng Motor Corporation Research and Development General Institute（东风汽车集团研发总院）；Dongfeng Yuexiang Technology Co., Ltd.（东风悦铃科技有限公司）
Imitation-Guided Bimanual Planning for Stable Manipulation under Changing External Forces
HRI；Istituto Italiano Di Tecnologia (IIT)（意大利技术研究所）；LASA, School of Engineering, EPFL（激光实验室，工程学院，瑞士联邦理工学院）；Guangdong University of Technology（广东技术大学）；The Technical University of Munich（慕尼黑技术大学）；The School of Computer Science, University of Nottingham（nottingham大学计算机科学学院）
