本文提出开源 Sim2Real 流水线，将 Frozen Lake 中训练的 Q-table 强化学习策略迁移到 12 自由度四足机器人，实现不依赖昂贵定位与建图传感器的网格自主导航与避障。
摘要：
本文提出一种 Sim2Real（Simulation to Reality，仿真到现实）方法，以弥合在仿真环境中训练的智能体与其在相似场景中导航机器人的真实世界部署之间的差距。具体而言，我们专注于在真实世界的类网格环境中导航四足机器人，该环境的灵感来自 Gymnasium Frozen Lake——一个非常用户友好且免费的应用程序编程接口（API），用于开发和测试强化学习（RL）算法。我们详细介绍了一条流水线的开发，该流水线将在 Frozen Lake 仿真中学到的运动策略迁移到实体四足机器人，从而能够在网格中实现自主导航和避障，而无需依赖昂贵的定位与建图传感器。该工作包括在 Frozen Lake 环境中训练 RL 智能体，并利用所得 Q-table 控制一台 12 自由度（DOF）四足机器人。除了详细说明 RL 实现、基于逆运动学的四足步态以及迁移策略流水线之外，我们还在 GitHub 上开源了该项目，并附上展示我们 Sim2Real 迁移方法的演示视频。本工作为研究人员、学生和爱好者提供了一个易用、直接且低成本的框架，用于在真实世界网格环境中探索和实现基于 RL 的机器人导航。
英文摘要：
This paper presents a Sim2Real (Simulation to Reality) approach to bridge the gap between a trained agent in a simulated environment and its real-world implementation in navigating a robot in a similar setting. Specifically, we focus on navigating a quadruped robot in a real-world grid-like environment inspired by the Gymnasium Frozen Lake -- a highly user-friendly and free Application Programming Interface (API) to develop and test Reinforcement Learning (RL) algorithms. We detail the development of a pipeline to transfer motion policies learned in the Frozen Lake simulation to a physical quadruped robot, thus enabling autonomous navigation and obstacle avoidance in a grid without relying on expensive localization and mapping sensors. The work involves training an RL agent in the Frozen Lake environment and utilizing the resulting Q-table to control a 12 Degrees-of-Freedom (DOF) quadruped robot. In addition to detailing the RL implementation, inverse kinematics-based quadruped gaits, and the transfer policy pipeline, we open-source the project on GitHub and include a demonstration video of our Sim2Real transfer approach. This work provides an accessible, straightforward, and low-cost framework for researchers, students, and hobbyists to explore and implement RL-based robot navigation in real-world grid environments.
The problem of multi-robot navigation of connectivity maintenance is challenging in multi-robot applications. This work investigates how to navigate a multi-robot team in unknown environments while maintaining connectivity. We propose a reinforcement learning (RL) approach to develop a decentralized policy, which is shared among multiple robots. Given range sensor measurements and the positions of other robots, the policy aims to generate control commands for navigation and preserve the global connectivity of the robot team. We incorporate connectivity concerns into the RL framework as constra…
Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26% reductio…
Imitation learning holds the promise to address challenging robotic tasks such as autonomous navigation. It however requires a human supervisor to oversee the training process and send correct control commands to robots without feedback, which is always prone to error and expensive. To minimize human involvement and avoid manual labeling of data in the robotic autonomous navigation with imitation learning, this paper proposes a novel semi-supervised imitation learning solution based on a multi-sensory design. This solution includes a suboptimal sensor policy based on sensor fusion to automatic…
Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with limited capabilities, while being restricted to few behavioral skills such as passive visual odometry (VO) or mobile robot visual localization. Here we propose an approach to unify those successful robot perception systems for active target-driven navigation tasks via reinforcement learning (RL). Our method temporally incorporates compact motion and visual p…
Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins University Applied Physics Lab（约翰斯·霍普金斯大学应用物理实验室）；UC Berkeley（加州大学伯克利分校）
Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments. While prior research has mostly focused on modeling pedestrians as independent, intentional individuals, people move in groups; consequently, it is imperative for mobile robots to respect human groups when navigating around people. This paper explores learning group-aware navigation policies based on dynamic group formation using deep reinforcement learning. Through simulation experiments, we show that group-aware policies, compared to baseline…
Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneously within dynamic environments. We apply deep reinforcement learning (DRL) to learn a decentralized end-to-end policy which maps raw sensor data to the command velocities of the agent. In order to enable the policy to generalize, the training is performed in different environments and scenarios. The learned policy is tested and evaluated in common multi-robot scenarios like switching a place, an intersection and a bottleneck situation. This policy allows the agent to recover from dead ends and…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multif…
Ohio State University（俄亥俄州立大学）；Ottonomy Inc.（Ottonomy公司）
The popularity of mobile robots has been steadily growing, with these robots being increasingly utilized to execute tasks previously completed by human workers. For bipedal robots to see this same success, robust autonomous navigation systems need to be developed that can execute in real-time and respond to dynamic environments. These systems can be divided into three stages: perception, planning, and control. A holistic navigation framework for bipedal robots must successfully integrate all three components of the autonomous navigation problem to enable robust real-world navigation. In this p…
Imperial College London（帝国理工学院）；AIOZ Ltd.（AIOZ有限公司）
Autonomous navigation is a long-standing field of robotics research, which provides an essential capability for mobile robots to execute a series of tasks on the same environments performed by human everyday. In this chapter, we present a set of algorithms to train and deploy deep networks for autonomous navigation of mobile robots using the Robot Operation System (ROS). We describe three main steps to tackle this problem: i) collecting data in simulation environments using ROS and Gazebo; ii) designing deep network for autonomous navigation, and iii) deploying the learned policy on mobile rob…
The Graduate Center（纽约市立大学研究生中心）；Hunter College of The City University of New York（纽约市立大学亨特学院）
While effective navigation in large, crowded environments is essential for an autonomous robot, preliminary testing of algorithms to support it requires simulation across a broad range of crowd scenarios. Most available simulation tools provide either realistic crowds without robots or realistic robots without realistic crowds. This paper introduces MengeROS, a 2-D simulator that realistically integrates multiple robots and crowds. MengeROS provides a broad range of settings in which to test the capabilities and performance of navigation algorithms designed for large crowded environments.
Long-range indoor navigation requires guiding robots with noisy sensors and controls through cluttered environments along paths that span a variety of buildings. We achieve this with PRM-RL, a hierarchical robot navigation method in which reinforcement learning agents that map noisy sensors to robot controls learn to solve short-range obstacle avoidance tasks, and then sampling-based planners map where these agents can reliably navigate in simulation; these roadmaps and agents are then deployed on robots, guiding them along the shortest path where the agents are likely to succeed. Here we use …
Cyprus University of Technology（塞浦路斯理工大学）；Technion Israel Institute of Technology（以色列理工学院）
This paper brings together the concepts of navigation transformation and harmonic functions to form navigation functions that are correct-by-construction in the sense that no tuning is required. The form of the navigation function is explicitly related to the number of obstacles in the environment. This enables application of navigation functions for autonomous robot navigation in partially or fully unknown environments, with the capability of on-the-fly adjustment of the navigation function when new obstacles are discovered by the robot. Appropriate navigation controllers, applicable to robot…
Natural language-based robotic navigation remains a challenging problem due to the human knowledge of navigation constraints, and destination is not directly compatible with the robot knowledge base. In this paper, we aim to translate natural destination commands into high-level robot navigation plans given a map of interest. We identify grammatically associated segments of destination description and recursively apply each of them to update a belief distribution of an area over the given map.We train a destination grounding model using a dataset of single-step belief update for precise, proxi…
Google Brain（谷歌大脑）；University of New Mexico（新墨西哥大学）
We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology. Next, the sampling-based planners provide roadmaps which connect robot configurations that can be successfully navigated by the RL agent. The same RL agents are used to control the robot under the direction of the planning, enabling long-range navigation. We use the Probabili…
Tsinghua University（清华大学）；University of Bath（巴斯大学）
Pointing gestures are widely used in robot navigationapproaches nowadays. However, most approaches only use point-ing gestures, and these have two major limitations. Firstly, they need to recognize pointing gestures all the time, which leads to long processing time and significant system overheads. Secondly,the user's pointing direction may not be very accurate, so the robot may go to an undesired place. To relieve these limitations,we propose a voice-guided pointing robot navigation approach named VGPN, and implement its prototype on a wheeled robot,TurtleBot 2. VGPN recognizes a pointing ges…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Despite the rapid advancement of navigation algorithms, mobile robots often produce anomalous behaviors that can lead to navigation failures. The ability to detect such anomalous behaviors is a key component in modern robots to achieve high-levels of autonomy. Reactive anomaly detection methods identify anomalous task executions based on the current robot state and thus lack the ability to alert the robot before an actual failure occurs. Such an alert delay is undesirable due to the potential damage to both the robot and the surrounding objects. We propose a proactive anomaly detection network…
Universidade de Pernambuco（伯南布哥大学）；Istituto Italiano di Tecnologia（意大利理工学院）
Dealing with social tasks in robotic scenarios is difficult, as having humans in the learning loop is incompatible with most of the state-of-the-art machine learning algorithms. This is the case when exploring Incremental learning models, in particular the ones involving reinforcement learning. In this work, we discuss this problem and possible solutions by analysing a previous study on adaptive convolutional encoders for a social navigation task.
We present a novel reinforcement learning (RL) based task allocation and decentralized navigation algorithm for mobile robots in warehouse environments. Our approach is designed for scenarios in which multiple robots are used to perform various pick up and delivery tasks. We consider the problem of joint decentralized task allocation and navigation and present a two level approach to solve it. At the higher level, we solve the task allocation by formulating it in terms of Markov Decision Processes and choosing the appropriate rewards to minimize the Total Travel Delay (TTD). At the lower level…
Visual homing is a lightweight approach to robot visual navigation. Based upon stored visual information of a home location, the navigation back to this location can be accomplished from any other location in which this location is visible by comparing home to the current image. However, a key challenge of visual homing is that the target home location must be within the robot's field of view (FOV) to start homing. Therefore, this work addresses such a challenge by integrating blockchain technology into the visual homing navigation system. Based on the decentralized feature of blockchain, the …
LAAS-CNRS（法国国家科学研究中心系统分析与架构实验室）；CNRS（法国国家科学研究中心）；Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工与自然智能研究所）
As more robots are being deployed into human environments, a human-aware navigation planner needs to handle multiple contexts that occur in indoor and outdoor environments. In this paper, we propose a tunable human-aware robot navigation planner that can handle a variety of humanrobot contexts. We present the architecture of the planner and discuss the features and some implementation details. Then we present a detailed analysis of various simulated humanrobot contexts using the proposed planner along with some quantitative results. Finally, we show the results in a real-world scenario after d…
Deep reinforcement learning (DRL) demonstrates its potential in learning a model-free navigation policy for robot visual navigation. However, the data-demanding algorithm relies on a large number of navigation trajectories in training. Existing datasets supporting training such robot navigation algorithms consist of either 3D synthetic scenes or reconstructed scenes. Synthetic data suffers from domain gap to the real-world scenes while visual inputs rendered from 3D reconstructed scenes have undesired holes and artifacts. In this paper, we present a new dataset collected in real-world to facil…
We present EWareNet, a novel intent and affect-aware social robot navigation algorithm among pedestrians. Our approach predicts the trajectory-based pedestrian intent from gait sequence, which is then used for intent-guided navigation taking into account social and proxemic constraints. We propose a transformer-based model that works on commodity RGB-D cameras mounted onto a moving robot. Our intent prediction routine is integrated into a mapless navigation scheme and makes no assumptions about the environment of pedestrian motion. Our navigation scheme consists of a novel obstacle profile rep…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；George Mason University（乔治梅森大学）；Everyday Robots（日常机器人公司）；Army Research Laboratory（陆军研究实验室）；Sony AI（索尼人工智能）
While current systems for autonomous robot navigation can produce safe and efficient motion plans in static environments, they usually generate suboptimal behaviors when multiple robots must navigate together in confined spaces. For example, when two robots meet each other in a narrow hallway, they may either turn around to find an alternative route or collide with each other. This paper presents a new approach to navigation that allows two robots to pass each other in a narrow hallway without colliding, stopping, or waiting. Our approach, Perceptual Hallucination for Hallway Passing (PHHP), l…
Autonomous navigation in dynamic environment heavily depends on the environment and its topology. Prior knowledge of the environment is not usually accurate as the environment keeps evolving in time. Since robot is continuously evaluating the environment as it proceeds, deciding the optimal way to traverse the environment to get to the goal, computationally efficient yet mathematically adaptive navigation algorithms are needed. In this paper, a navigation scheme for mobile robot, capable of dealing with time variant environment is proposed. This approach consists of a global planner (A*) and l…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Sony AI（索尼人工智能）
This paper presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods require environment-specific in-situ system adjustment, e.g. from human experts, or may repeat their mistakes regardless of how many times they have navigated in the same environment. Having the potential to improve with experience, learning-based navigation is highly dependent on access to training resources, e.g. sufficient memory and fast computation, and is prone to forgetting previously learned capability, especially when facing diff…
Robots moving safely and in a socially compliant manner in dynamic human environments is an essential benchmark for long-term robot autonomy. However, it is not feasible to learn and benchmark social navigation behaviors entirely in the real world, as learning is data-intensive, and it is challenging to make safety guarantees during training. Therefore, simulation-based benchmarks that provide abstractions for social navigation are required. A framework for these benchmarks would need to support a wide variety of learning approaches, be extensible to the broad range of social navigation scenar…
A new class of continuum robots has recently been explored, characterized by tip extension, significant length change, and directional control. Here, we call this class of robots "vine robots," due to their similar behavior to plants with the growth habit of trailing. Due to their growth-based movement, vine robots are well suited for navigation and exploration in cluttered environments, but until now, they have not been deployed outside the lab. Portability of these robots and steerability at length scales relevant for navigation are key to field applications. In addition, intuitive human-in-…
LAAS-CNRS, Universit de Toulouse, CNRS（法国国家科学研究中心系统分析与架构实验室，图卢兹大学，法国国家科学研究中心）
We claim that navigation in human environments can be viewed as cooperative activity especially in constrained situations. Humans concurrently aid and comply with each other while moving in a shared space. Cooperation helps pedestrians to efficiently reach their own goals and respect conventions such as the personal space of others. To meet human comparable efficiency, a robot needs to predict the human trajectories and plan its own trajectory correspondingly in the same shared space. In this work, we present a navigation planner that is able to plan such cooperative trajectories, simultaneous…
In this paper, we present a framework for real-time autonomous robot navigation based on cloud and on-demand databases to address two major issues of human-like robot interaction and task planning in global dynamic environment, which is not known a priori. Our framework contributes to make human-like brain GPS mapping system for robot using spatial information and performs 3D visual semantic SLAM for independent robot navigation. We accomplish the feat by separating robot's memory system into Long-Term Memory (LTM) and Short-Term Memory (STM). We also form robot's behavior and knowledge system…
Moving in dynamic pedestrian environments is one of the important requirements for autonomous mobile robots. We present a model-based reinforcement learning approach for robots to navigate through crowded environments. The navigation policy is trained with both real interaction data from multi-agent simulation and virtual data from a deep transition model that predicts the evolution of surrounding dynamics of mobile robots. The model takes laser scan sequence and robot's own state as input and outputs steering control. The laser sequence is further transformed into stacked local obstacle maps …
This paper shows the achievement of a sensing and navigation system of aerial robot for measuring location and size of trees in a forest environment autonomously. Although forestry is an important industry in Japan, the working population of forestry is decreasing. Then, as an application of mechanization of forestry, we propose tree data collection system by aerial robots which have high mobility in three-dimensional space. First, we develop tree recognition and measurement method, along with algorithm to generate tree database. Second, we describe aerial robot navigation system based on tree…
University of Science and Technology of China（中国科学技术大学）
This paper proposes an end-to-end deep reinforcement learning approach for mobile robot navigation with dynamic obstacles avoidance. Using experience collected in a simulation environment, a convolutional neural network (CNN) is trained to predict proper steering actions of a robot from its egocentric local occupancy maps, which accommodate various sensors and fusion algorithms. The trained neural network is then transferred and executed on a real-world mobile robot to guide its local path planning. The new approach is evaluated both qualitatively and quantitatively in simulation and real-worl…
We are interested in the design of autonomous robot behaviors that learn the preferences of users over continued interactions, with the goal of efficiently executing navigation behaviors in a way that the user expects. In this paper, we discuss our work in progress to modify a general model for robot navigation behaviors in an exploration task on a per-user basis using preference-based reinforcement learning. The novel contribution of this approach is that it combines reinforcement learning, motion planning, and natural language processing to allow an autonomous agent to learn from sustained d…
Human navigation in built environments depends on symbolic spatial information which has unrealised potential to enhance robot navigation capabilities. Information sources such as labels, signs, maps, planners, spoken directions, and navigational gestures communicate a wealth of spatial information to the navigators of built environments; a wealth of information that robots typically ignore. We present a robot navigation system that uses the same symbolic spatial information employed by humans to purposefully navigate in unseen built environments with a level of performance comparable to human…
This work proposes a novel transformation termed the conformal navigation transformation to achieve collision-free navigation of a robot in a workspace populated with arbitrary polygonal obstacles. The properties of the conformal navigation transformation in the polygonal workspace are investigated in this work as well as its capability to provide a solution to the navigation problem. %The properties of the conformal navigation transformation are investigated, which contribute to the solution of the robot navigation problem in complex polygonal environments. %which facilitates the navigation o…
Pontificia Universidad Catolica de Chile（智利天主教大学）；Millennium Institute for Foundational Research on Data（千年基础数据研究所）
We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navigation. We follow the framework established by (Zang et al., 2018a) that proposes the use of a navigation graph as a knowledge base for the task. Our results show significant performance gains when translating instructions on previously unseen environments, therefore, improving the generalization capabilities of the model.
