连续软体机器人的结构范型与形态复现

为提出连续软体机器人的设计与分析通用理论,根据当前连续软体机器人的运动特征和细长软体生物纵肌结构抽象出通用的结构范型（GSP）,并由此建立了连续软体机器人在驱动空间、构型空间和任务空间中的一般运动学．针对这类机器人在构型空间中灵活运动或操作的需求,提出一种细长软体机器人对任意目标曲线的形态复现算法,并采用离散Fréchet距离评价形态复现的相似性．通过仿真和实验,以形状记忆合金（SMA）弹簧驱动的双软体模块机器人为例验证了结构范型与一般运动学的正确性．此外,以仿生运动曲线等为目标曲线,以组合案例分析曲线形状、关节数量和关节参数对复现效果的影响．结果表明,软体单元模块数量越多或其最大弯曲角越大,形态复现的相似性越高．     

位－力驱动的线驱连续型机器人的动力学建模及实验验证

提出了一种位－力混合驱动的线驱连续型机器人的动力学模型。首先,基于集中质量矩阵法进行机器人动力学建模,将机器人动能的连续积分等效离散为三点求和形式,可简化建模过程并提升仿真的计算效率。其次,分析了驱动力与驱动线几何约束的力学关系,将线驱动作用等效建模为电机的驱动参数与牵引线张力的线性方程组,不仅可以精确地满足牵引线对系统的约束条件,还可以在不使用拉力传感器的条件下得到线的驱动力,降低了机器人成本及控制难度,这种方法适用于任意数量牵引线的连续型机器人。最后,将线驱连续型机器人的仿真和实验结果进行对比,机器人末端点的轨迹最大误差为3.85%,验证了所提模型的有效性。     

Multi-level control architecture for Bionic Handling Assistant robot augmented by learning from demonstration for apple-picking

The control of soft continuum robots is challenging owing to their mechanical elasticity and complex dynamics. An additional challenge emerges when we want to apply Learning from Demonstration (LfD) and need to collect necessary demonstrations due to the inherent control difficulty. In this paper, we provide a multi-level architecture from low-level control to high-level motion planning for the Bionic Handling Assistant (BHA) robot. We deploy learning across all levels to enable the application of LfD for a real-world manipulation task. To record the demonstrations, an actively compliant controller is used. A variant of dynamical systems' application that are able to encode both position and orientation then maps the recorded 6D end-effector pose data into a virtual attractor space. A recent LfD method encodes the pose attractors within the same model for point-to-point motion planning. In the proposed architecture, hybrid models that combine an analytical approach and machine learning techniques are used to overcome the inherent slow dynamics and model imprecision of the BHA. The performance and generalization capability of the proposed multi-level approach are evaluated in simulation and with the real BHA robot in an apple-picking scenario which requires high accuracy to control the pose of the robot's end-effector.     

Software toolkit for modeling,simulation, and control of soft robots

The technological differences between traditional robotics and soft robotics have an impact on all of the modeling tools generally in use, including direct kinematics and inverse models, Jacobians, and dynamics. Due to the lack of precise modeling and control methods for soft robots, the promising concepts of using such design for complex applications (medicine, assistance, domestic robotics, etc.) cannot be practically implemented. This paper presents a first unified software framework dedicated to modeling, simulation, and control of soft robots. The framework relies on continuum mechanics for modeling the robotic parts and boundary conditions like actuators and contacts using a unified representation based on Lagrange multipliers. It enables the digital robot to be simulated in its environment using a direct model. The model can also be inverted online using an optimization-based method which allows to control the physical robots in the task space. To demonstrate the effectiveness of the approach, we present various soft robots scenarios including ones where the robot is interacting with its environment. The software has been built on top of SOFA, an open-source framework for deformable online simulation and is available at https://project.inria.fr/softrobot/.     

基于人工情感的拟人机器人控制体系结构

简要概括了当前人工情感的应用，提出一种基于人工情感的拟人机器人控制体系结构，并给出了仿真示例．基于情感的控制结构具有混合分层的特点，情感状态影响到机器人的整个信息处理过程．这种结构不仅体现了机器人的个性化，同时增强了机器人在动态环境中的学习和自适应能力．     

A novel continuum robotic cable aimed at applications in space

We introduce a new class of long and thin continuum robots intended for use in space applications. This ‘cable’ robot is a next-generation version of the current state of the art (NASA’s ‘Tendril’). The article describes the key practical limitations of the mechanical design of ‘Tendril’. We introduce the design specifics of our novel concept for a next-generation device with significantly enhanced performance. Equipped with a light and compact motor-encoder actuation mechanism, the new design has improved compliance and possesses a concentric backbone arrangement which is tendon-actuated and spring-loaded. A new forward kinematic model is developed extending the established models for constant-curvature continuum robots, to account for the new design feature of controllable compression (in the hardware). The model is validated by performing experiments with a three-section prototype of the design. The new model is found to be effective as a baseline to predict the performance of such long and thin continuum ‘cable’ robots.     

Bio-insect and artificial robot interaction: learning mechanism and experiment

This paper addresses fuzzy-logic-based reinforcement learning architecture and experimental results for the interaction between an artificial robot and a living bio-insect. The main goal of this research is to drag the bio-insect towards the desired goal area without any human aid. To achieve the goal, we seek to design robot intelligence architecture such that the robot can drag the bio-insect using its own learning mechanism. The main difficulties of this research are to find an interaction mechanism between the robot and bio-insect and to design a robot intelligence architecture. In simple interaction experiment, the bio-insect does not react to stimuli such as light, vibration, or artificial robot motion. From various trials-and-error efforts, we empirically found an actuation mechanism for the interaction between the robot and bio-insect. Nevertheless, it is difficult to control the movement of the bio-insect due to its uncertain and complex behavior. For the artificial robot, we design a fuzzy-logic-based reinforcement learning architecture that helps the artificial robot learn how to control the movement of the bio-insect under uncertain and complex behavior. Here, we present the experimental results regarding the interaction between an artificial robot and a bio-insect.     

软体机器人手眼视觉/形状混合控制

当末端带有相机的连续型软体机器人进行作业时,由于避障、安全性等多方面因素,既需要末端相机－机器人系统的视觉伺服,也需要机器人的整体形状控制．针对这个问题,本文提出了一种软体机器人手眼视觉/形状混合控制方法．该方法无需知道空间特征点的3维坐标,只需给定特征点在末端相机像平面的期望像素坐标和软体机器人的期望形状就可达到控制目的．建立了软体机器人的运动学模型,利用该模型,结合深度无关交互矩阵自适应手眼视觉控制和软体机器人形状控制,提出了一种混合控制律,并用李亚普诺夫稳定性理论对该控制律进行证明．仿真和实验的结果均表明,末端相机特征点像素坐标和形状可以收敛到期望值．     

一种空间仿生柔性机器人设计与智能规划仿真方法

针对传统空间刚体机器人存在的自由度有限和环境适应性差等缺陷,基于生物体结构提出了一种受“尺蠖”与“蛇”启发的适用于空间在轨服务的柔性机器人。首先,搭建了柔性机器人原型样机,研究了镍钛形状记忆合金（SMA）驱动器的驱动特性,设计了可视化控制界面并通过实物实验验证了机器人原型样机的可操控性。然后,设计了一种基于所提柔性机器人结构的Q学习算法和相应的奖励函数,搭建了柔性机器人仿真模型并在仿真环境中完成了基于Q学习的机器臂自主学习规划仿真实验。实验结果显示机器臂能够在较短时间内收敛到稳定状态并自主完成规划任务,表明所提出算法具有有效性和可行性,强化学习方法在柔性机器人的智能规划与控制中具有良好的应用前景。     

A study on effect of biarticular muscles in an antagonistically actuated robot arm through numerical simulations

Control of articulated robots by biarticular actuation has recently attracted great attention in the research field of robotics. Although many of studies concerned with this issue deal with legged robots or robot arms kinetically interacting with environment such as a floor or an object, motion control of an articulated robot arm with no kinetic interaction is also an interesting topic of biarticular actuation. In the motion control, a major issue is how it is possible for biarticular actuation to contribute to improvement of control; however, showing a clear finding for this issue seems to be considerably difficult. This paper considers a study for exploring that issue. Biarticular actuation usually constitutes a redundant actuation system; therefore, control of a robot arm to a desired posture can be achieved by many combinations of actuator forces. Based on this feature, this paper considers three typical combinations of actuator forces. Point-to-point control of the robot is performed for each of the combinations in simulation, and control performances of the combinations are compared with each other. In addition, the performances are compared with that of monoarticular actuation. In those comparisons, two of the three combinations show similar control performances, which suggests possibility of major contribution of biarticular actuators to motion control of a robot arm. On the other hand, control performance of the other combination is similar to that of monoarticular actuation, rather than those of other two combinations.     

Rapid, safe, and incremental learning of navigation strategies

In this paper we propose a reinforcement connectionist learning architecture that allows an autonomous robot to acquire efficient navigation strategies in a few trials. Besides rapid learning, the architecture has three further appealing features. First, the robot improves its performance incrementally as it interacts with an initially unknown environment, and it ends up learning to avoid collisions even in those situations in which its sensors cannot detect the obstacles. This is a definite advantage over nonlearning reactive robots. Second, since it learns from basic reflexes, the robot is operational from the very beginning and the learning process is safe. Third, the robot exhibits high tolerance to noisy sensory data and good generalization abilities. All these features make this learning robot's architecture very well suited to real-world applications. We report experimental results obtained with a real mobile robot in an indoor environment that demonstrate the appropriateness of our approach to real autonomous robot control.     

Soft Robotics: Morphology and Morphology-inspired Motion Strategy

Robotics has aroused huge attention since the 1950s. Irrespective of the uniqueness that industrial applications exhibit, conventional rigid robots have displayed noticeable limitations, particularly in safe cooperation as well as with environmental adaption. Accordingly, scientists have shifted their focus on soft robotics to apply this type of robots more effectively in unstructured environments. For decades, they have been committed to exploring sub-fields of soft robotics (e.g., cutting-edge techniques in design and fabrication, accurate modeling, as well as advanced control algorithms). Although scientists have made many different efforts, they share the common goal of enhancing applicability. The presented paper aims to brief the progress of soft robotic research for readers interested in this field, and clarify how an appropriate control algorithm can be produced for soft robots with specific morphologies. This paper, instead of enumerating existing modeling or control methods of a certain soft robot prototype, interprets for the relationship between morphology and morphology-dependent motion strategy, attempts to delve into the common issues in a particular class of soft robots, and elucidates a generic solution to enhance their performance.      

Socially guided intrinsic motivation for robot learning of motor skills

This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our algorithmic architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line, we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.     

Reusable robot system for display and disposal tasks at convenience stores based on a SysML model and RT Middleware

Service robots are increasingly being expected to replace human labor; however, in practical settings, these robots have not been fully utilized, partly because the applications that service robots are expected are quite broad. Suitable hardware and software should be developed in order to cope with a wide variety of applications. Ideally, these resources should be developed using common hardware and software platforms are required. Middleware platforms for robotics software, such as ROS and RT Middleware, have already been developed. However, these platforms still face reusability problems due to the inconsistency present in system architectures. Systems are typically assumed to be reused with a given architecture, and if the user-side software architecture is inconsistent with this assumption, the system's reusability suffers. To address this issue, we propose a procedure for optimizing system development using SysML. In this study, our robot system is designed to complete a display disposal tasks in a convenience store; we verify the validity of the robot system using this task. In addition, to verify the reusability of the developed robot system, we employ system functions developed for another task and demonstrate their reuse and operation.     

Cognitive Architecture for Robust Adaptive Control of Robots in a Team

The objective of this paper is to present a cognitive architecture thatutilizes three different methodologies for adaptive, robust control ofrobots behaving intelligently in a team. The robots interact within a worldof objects, and obstacles, performing tasks robustly, while improving theirperformance through learning. The adaptive control of the robots has beenachieved by a novel control system. The Tropism-based cognitive architecturefor the individual behavior of robots in a colony is demonstrated throughexperimental investigation of the robot colony. This architecture is basedon representation of the likes and dislikes of the robots. It is shown thatthe novel architecture is not only robust, but also provides the robots withintelligent adaptive behavior. This objective is achieved by utilization ofthree different techniques of neural networks, machine learning, and geneticalgorithms. Each of these methodologies are applied to the tropismarchitecture, resulting in improvements in the task performance of the robotteam, demonstrating the adaptability and robustness of the proposed controlsystem.     

Indirect robot model learning for tracking control

Learning task-space tracking control on redundant robot manipulators is an important but difficult problem. A main difficulty is the non-uniqueness of the solution: a task-space trajectory has multiple joint-space trajectories associated, therefore averaging over non-convex solution space needs to be done if treated as a regression problem. A second class of difficulties arise for those robots when the physical model is either too complex or even not available. In this situation machine learning methods may be a suitable alternative to classical approaches. We propose a learning framework for tracking control that is applicable for underactuated or non-rigid robots where an analytical physical model of the robot is unavailable. The proposed framework builds on the insight that tracking problems are well defined in the joint task- and joint-space coordinates and consequently predictions can be obtained via local optimization. Physical experiments show that state-of-the art accuracy can be achieved in both online and offline tracking control learning. Furthermore, we show that the presented method is capable of controlling underactuated robot architectures as well.     

ALECSYS and the AutonoMouse: Learning to Control a Real Robot by Distributed Classifier Systems

In this article we investigate the feasibility of using learning classifier systems as a tool for building adaptive control systems for real robots. Their use on real robots imposes efficiency constraints which are addressed by three main tools: parallelism, distributed architecture, and training. Parallelism is useful to speed up computation and to increase the flexibility of the learning system design. Distributed architecture helps in making it possible to decompose the overall task into a set of simpler learning tasks. Finally, training provides guidance to the system while learning, shortening the number of cycles required to learn. These tools and the issues they raise are first studied in simulation, and then the experience gained with simulations is used to implement the learning system on the real robot. Results have shown that with this approach it is possible to let the AutonoMouse, a small real robot, learn to approach a light source under a number of different noise and lesion conditions.This work was partially written while the author was at International Computer Science Institute, 1947 Center Street, Suite 600, Berkeley, 94704-1198 California, USA.     

Practical Kinematics for Real-Time Implementation of Continuum Robots

This paper introduces three algorithms which are essential for the practical, real-time implementation of continuum robots. Continuum robots lack the joints and links which compose traditional and high-degree-of-freedom robots, instead relying on finite actuation mechanisms to shape the robot into a smooth curve. Actuator length limits shape the configuration or joint space of continuum manipulators, introducing couplings analyzed in this paper which must be understood to make effective use of continuum robot hardware. Based on the new understanding of the configuration space uncovered, this paper then derives the workspace of continuum robots when constrained by actuator length limits. Finally, a tangle/untangle algorithm correctly computes the shape of the distal segments of multisection tendon-actuated continuum robots. These contributions are essential for effective use of a wide range of continuum robots, and have been implemented and tested on two different types of continuum robots. Results and insight gained from this implementation are presented     

机器人班组的自组织递阶控制

研究了机器人班组在执行各种任务时的协调控制.由于机器人班组是由多个能力有限的 机器人组成的,被操作的对象可以是一个刚体、柔性体或机械系统,而且需要跟踪的运动也可 以是各种各样的,所以整个系统是相当复杂的.这样的机械系统,按其力学性质可以将要实现 的控制任务加以分解,从而实现递阶控制,各层的控制只完成被分解出来的特定的较简单的任 务,而各机器人之间的协调由自组织算法自动完成.     

A Neural Network Controller for Continuum Robots

Continuum or hyper-redundant robot manipulators can exhibit behavior similar to biological trunks, tentacles, or snakes. Unlike traditional rigid-link robot manipulators, continuum robot manipulators do not have rigid joints, hence these manipulators are extremely dexterous, compliant, and are capable of dynamic adaptive manipulation in unstructured environments. However, the development of high-performance control algorithms for these manipulators is quite a challenge, due to their unique design and the high degree of uncertainty in their dynamic models. In this paper, a controller for continuum robots, which utilizes a neural network feedforward component to compensate for dynamic uncertainties is presented. Experimental results using the OCTARM, which is a soft extensible continuum manipulator, are provided to illustrate that the addition of the neural network feedforward component to the controller provides improved performance.