离线导航演示具有多模态特性，因为同一观测结果往往对应多个有效动作，例如从障碍物两侧通过。行为克隆会对这些动作取平均，可能导致不安全的路径。多模态策略必须从数据中发现这些备选方案，但相似状态可能导致不同路径，其当前动作存在重叠。在导航场景中，这些备选方案具有几何成因，可从单一观测结果计算得出。我们提出一种分层神经网络策略，该策略从局部几何计算候选模式，并从演示中学习应遵循哪种模式以及如何执行。高层策略利用目标和其在一组候选模式中的先前选择来选择模式，低层策略将该模式转化为具体动作。在仿真环境中，该策略在已见和未见测试案例中的成功率超过95%，而四个离线学习基线的成功率最高分别为43%和20%，采用相同模式但不进行学习的启发式方法的成功率最高分别为79%和67%。经仿真训练的策略还可迁移至LimX Tron 1双足机器人。
英文摘要：
Offline navigation demonstrations are multimodal, because one observation often allows several valid actions, such as passing an obstacle on either side. Behavior cloning averages these actions, potentially leading to unsafe routes. Multimodal policies must discover the alternatives from the data, but similar states can lead to different routes whose current actions overlap. In navigation, the alternatives have a geometric cause and can be computed from one observation. We propose a hierarchical neural-network policy that computes candidate modes from local geometry and learns from demonstrations which mode to follow and how. A high-level policy selects a mode using the goal and its previous choice among a set of candidate modes, and a low-level policy turns it into an action. In simulation, the policy succeeds in over 95\% of seen and unseen test cases, compared with at most 43\% and 20\% for four offline learning baselines and 79\% and 67\% for a heuristic that uses the same modes without learning. The simulation-trained policy also transfers to a LimX Tron 1 bipedal robot.
ETH Zurich（苏黎世联邦理工学院）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-苏黎世联邦理工学习系统中心）
This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation learning (IL) and reinforcement learning (RL). While RL and IL suffer from a large sample complexity and the distribution mismatch problem, respectively, we show that leveraging prior expert demonstrations for pre-training can reduce the training time to reach at least the same level of performance compared to plain RL by a factor of 5. We present a thorough ev…
Enhanced Robotic Navigation in Deformable Environments using Learning from Demonstration and Dynamic Modulation
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Germany（慕尼黑机器人与机器智能研究所（MIRMI），慕尼黑技术大学（TUM））；Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（穆罕默德·本·扎耶德人工智能大学）
University of California, Berkeley（加州大学伯克利分校）；Robotics at Google（谷歌机器人学）
Imitation learning is a popular approach for training visual navigation policies. However, collecting expert demonstrations for legged robots is challenging as these robots can be hard to control, move slowly, and cannot operate continuously for a long time. Here, we propose a zero-shot imitation learning approach for training a visual navigation policy on legged robots from human (third-person perspective) demonstrations, enabling high-quality navigation and cost-effective data collection. However, imitation learning from third-person demonstrations raises unique challenges. First, these demo…
Army Research Laboratory（陆军研究实验室）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner. However, when facing new environments, these systems generally require re-tuning by expert roboticists with a good understanding of the inner workings of the navigation system. In contrast, even users who are unversed in the details of robot navigation algorithms can generate desirable navigation behavior in new environments via teleoperation. In this paper, we introduce APPLD, Adaptive Planner Parameter Learning from Demonstration, that allows existing navigation systems to …
Learning from Demonstration with Failure Awareness for Safe Robot Navigation
Department of Mechanical Engineering, The Hong Kong Polytechnic University（香港理工大学机械工程系）；College of Information Science and Technology, Eastern Institute of Technology（东华理工大学信息科学学院）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（香港理工大学航空与航空工程系）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Army Research Laboratory（陆军研究实验室）；Google（谷歌）
Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a 'socially compliant' manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human populated environments (e.g., domestic service robots in homes and restaurants and food delivery robots on public sidewalks), incorporating socially compliant navigation behaviors on these robots becomes critical to ensuring safe and comfortable human robot coexistence. To address this challenge, imitation learning is a promising framework, since …
Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator. However, the assumption limits the usage of imitation learning, especially when collecting demonstrations for the imitator is difficult. In this paper, we study out-of-dynamics imitation learning (OOD-IL), which relaxes the assumption to that the demonstrator and the imitator have the same state spaces but could have different action spaces and dynamics. OOD-IL enables imitation learning to utilize demonstrations from a wide range of demonstrators but intr…
Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
Systems Engineering Department, Federal University of Santa Catarina, Florianopolis, Brazil Faculty of Science；Engineering, Information Technology Åbo Akademi University, Finland
Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes to learning sensorimotor control policies from human demonstrations. Extraneous data modalities can lead to state over-specification, where the state contains modalities that are not only useless for decision-making but also can change data distribution across environments. State over-specification leads to issues such as the learned policy not generalizing outside of the training data distribution. In this work, we …
DINO-CVA: A Multimodal Goal-Conditioned Vision-to-Action Model for Autonomous Catheter Navigation
Gina Cody School of Engineering and Computer Science, Concordia University（甘娜·柯迪工程与计算机科学学院，康科迪亚大学）；The Wilfred and Joyce Posluns Centre for Image Guided Innovation & Therapeutic Intervention (PCIGITI) at the Hospital for Sick Children (SickKids)（威廉与乔伊斯·波斯卢斯影像引导创新与治疗干预中心（PCIGITI）（SickKids医院））；Electrical and Computer Engineering Department, Kettering University（电气与计算机工程系，凯特林大学）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Army Research Laboratory（陆军研究实验室）；Sony AI（索尼人工智能）
While imitation learning for vision based autonomous mobile robot navigation has recently received a great deal of attention in the research community, existing approaches typically require state action demonstrations that were gathered using the deployment platform. However, what if one cannot easily outfit their platform to record these demonstration signals or worse yet the demonstrator does not have access to the platform at all? Is imitation learning for vision based autonomous navigation even possible in such scenarios? In this work, we hypothesize that the answer is yes and that recent …
Johns Hopkins University（约翰斯·霍普金斯大学）；Wilmer Eye Institute at the Johns Hopkins Hospital（约翰斯·霍普金斯医院威尔默眼科研究所）
A fundamental challenge in retinal surgery is safely navigating a surgical tool to a desired goal position on the retinal surface while avoiding damage to surrounding tissues, a procedure that typically requires tens-of-microns accuracy. In practice, the surgeon relies on depth-estimation skills to localize the tool-tip with respect to the retina in order to perform the tool-navigation task, which can be prone to human error. To alleviate such uncertainty, prior work has introduced ways to assist the surgeon by estimating the tool-tip distance to the retina and providing haptic or auditory fee…
The Hong Kong University of Science and Technology（香港科技大学）
All-day and all-weather navigation is a critical capability for autonomous driving, which requires proper reaction to varied environmental conditions and complex agent behaviors. Recently, with the rise of deep learning, end-to-end control for autonomous vehicles has been well studied. However, most works are solely based on visual information, which can be degraded by challenging illumination conditions such as dim light or total darkness. In addition, they usually generate and apply deterministic control commands without considering the uncertainties in the future. In this paper, based on im…
Asan Medical Center, University of Ulsan College of Medicine（蔚山大学医学院峨山医学中心）；Medipixel, Inc.（Medipixel 公司）；Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine（蔚山大学医学院峨山医学中心峨山融合科学技术研究所）；Chungnam National University Sejong Hospital, Chungnam National University School of Medicine（忠南大学医学院世宗医院）
In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning(RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human dem…
CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology（宁波工程学院）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）
University of Massachusetts Dartmouth（马萨诸塞大学达特茅斯分校）；United States Army Research Laboratory（美国陆军研究实验室）
Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown to be advantageous for navigation tasks as it allows for machine learning non-experts to quickly provide information needed to learn complex traversal behaviors. However, a minimal set of demonstrations is unlikely to capture all relevant information needed to achieve the desired behavior in every possible future operational environment. Due to distributional shift among environments, a robot may encounter features t…
University of Bonn（波恩大学）；Fraunhofer FKIE（弗劳恩霍夫通信、信息处理与人机工程研究所）
For the most comfortable, human-aware robot navigation, subjective user preferences need to be taken into account. This paper presents a novel reinforcement learning framework to train a personalized navigation controller along with an intuitive virtual reality demonstration interface. The conducted user study provides evidence that our personalized approach significantly outperforms classical approaches with more comfortable human-robot experiences. We achieve these results using only a few demonstration trajectories from non-expert users, who predominantly appreciate the intuitive demonstrat…
Imperial College London（帝国理工学院）；AIOZ Pte Ltd（AIOZ私人有限公司）
Autonomous navigation in complex environments is a crucial task in time-sensitive scenarios such as disaster response or search and rescue. However, complex environments pose significant challenges for autonomous platforms to navigate due to their challenging properties: constrained narrow passages, unstable pathway with debris and obstacles, or irregular geological structures and poor lighting conditions. In this work, we propose a multimodal fusion approach to address the problem of autonomous navigation in complex environments such as collapsed cites, or natural caves. We first simulate the…
Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework
ShanghaiTech University（上海科技大学）；Harbin Institute of Technology（哈尔滨工业大学）；University of Shanghai for Science and Technology（上海理工大学）；The University of Manchester（曼彻斯特大学）；University College London（伦敦大学学院）
Learning Social Navigation from Positive and Negative Demonstrations and Rule-Based Specifications
Department of Artificial Intelligence, Korea University（人工智能系，韩国大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Department of Artificial Intelligence, Yonsei University（人工智能系，yonsei大学）；Robotics Institute, School of Computer Science at Carnegie Mellon University（机器人研究所，卡内基梅隆大学计算机科学学院）；Mobinn；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Statistics（统计学系）
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Department of Informatics, Graduate School of Informatics, Kyoto University（信息学系，京都大学研究生院）；Spatial Robotics Research Center, Fujitsu Limited（空间机器人研究中心，富士通有限公司）
IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations
Nanyang Technological University（南洋理工大学）；Carnegie Mellon University（卡内基梅隆大学）；The Chinese University of Hong Kong（香港中文大学）；A*STAR Institute for Infocomm Research (I2R)（新加坡科技研究局资讯通信研究院）
US Army Research Laboratory（美国陆军研究实验室）；Carnegie Mellon University（卡内基梅隆大学）
When working alongside human collaborators in dynamic and unstructured environments, such as disaster recovery or military operation, fast field adaptation is necessary for an unmanned ground vehicle (UGV) to perform its duties or learn novel tasks. In these scenarios, personnel and equipment are constrained, making training with minimal human supervision a desirable learning attribute. We address the problem of making UGVs more reliable and adaptable teammates with a novel framework that uses visual perception and inverse optimal control to learn traversal costs for environment features. Thro…
STEGNav: Spatio-Temporal Event Graph Reasoning for Multimodal Lifelong Object Navigation
State Key Laboratory of Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
Bio-inspired vehicles are currently leading the way in the quest to produce a vehicle capable of flight and underwater navigation. However, a fully functional vehicle has not yet been realized. We present the first fully functional vehicle platform operating in air and underwater with seamless transition between both mediums. These unique capabilities combined with the hovering, high maneuverability and reliability of multirotor vehicles, results in a disruptive technology for both civil and military application including air/water search and rescue, inspection, repairs and survey missions amo…
StepNav: Structured Trajectory Priors for Efficient and Multimodal Visual Navigation
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间利用技术与工程中心）
Australian Centre for Field Robotics（澳大利亚野外机器人学中心）；University of Sydney（悉尼大学）
Seamlessly operating an autonomous vehicle in a crowded pedestrian environment is a very challenging task. This is because human movement and interactions are very hard to predict in such environments. Recent work has demonstrated that reinforcement learning-based methods have the ability to learn to drive in crowds. However, these methods can have very poor performance due to inaccurate predictions of the pedestrians' future state as human motion prediction has a large variance. To overcome this problem, we propose a new method, SARL-SGAN-KCE, that combines a deep socially aware attentive val…
Mobile telepresence robots (MTRs) have become increasingly popular in the expanding world of remote work, providing new avenues for people to actively participate in activities at a distance. However, humans operating MTRs often have difficulty navigating in densely populated environments due to limited situation awareness and narrow field-of-view, which reduces user acceptance and satisfaction. Shared autonomy in navigation has been studied primarily in static environments or in situations where only one pedestrian interacts with the robot. We present a multimodal shared autonomy approach, le…
PRISM: Multimodal Terrain Mapping for Rover Navigation in Unstructured Environments
SnT, University of Luxembourg（卢森堡大学安全、可靠性和信任跨学科中心）；Department of Automation and Systems Engineering, Universidad de Málaga, Andalucía Tech（马拉加大学自动化与系统工程系，安达卢西亚技术大学）
