基于遗传算法的多机器人系统最优轨迹规划

针对关节型多机器人系统在静态环境下的点到点的轨迹规划问题,提出了一种基于遗传算法的最优轨迹规划策略.采用遗传算法在综合考虑各机器人沿轨迹运动的安全性、运动代价以及运动学约束的基础上为单个机器人规划最优的运动轨迹,并通过协调各机器人沿预定轨迹运行的时间避免机器人之间碰撞的发生.针对含有3个二自由度平面关节型机器人的多机器人系统进行了仿真实验,实验结果验证了该方法的有效性.     

Incremental statistical learning for integrating motion primitives and language in humanoid robots

We describe a novel approach that allows humanoid robots to incrementally integrate motion primitives and language expressions, when there are underlying natural language and motion language modules. The natural language module represents sentence structure using word bigrams. The motion language module extracts the relations between motion primitives and the relevant words. Both the natural language module and the motion language module are expressed as probabilistic models and, therefore, they can be integrated so that the robots can both interpret observed motion in the form of sentences and generate the motion corresponding to a sentence command. Incremental learning is needed for a robot that develops these linguistic skills autonomously . The algorithm is derived from optimization of the natural language and motion language modules under constraints on their probabilistic variables such that the association between motion primitive and sentence in incrementally added training pairs is strengthened. A test based on interpreting observed motion in the forms of sentence demonstrates the validity of the incremental statistical learning algorithm.     

Optimal behaviour prediction using a primitive-based data-driven model-free iterative learning control approach

This paper suggests an optimal behaviour prediction mechanism for Multi Input-Multi Output control systems in a hierarchical control system structure, using previously learned solutions to simple tasks called primitives. The optimality of the behaviour is formulated as a reference trajectory tracking problem. The primitives are stored in a library of pairs of reference input/controlled output signals. The reference input primitives are optimized at the higher hierarchical level in a model-free iterative learning control (MFILC) framework without using knowledge of the controlled process. Learning of the reference input primitives is performed in a reduced subspace using radial basis functions for approximations. The convergence of the MFILC learning scheme is achieved via a Virtual Reference Feedback Tuning design of the feedback controllers in the lower level feedback control loops. The new complex trajectories to be tracked are decomposed into the output primitives regarded as basis functions. Next, the optimal reference input fed to the control system in order to track the desired new trajectory is then recomposed from the reference input primitives. The efficiency of this approach is demonstrated on a case study concerning the control of a two-axis positioning mechanism, and the experimental validation is offered.     

Real-time Unsupervised Segmentation of human whole-body motion and its application to humanoid robot acquisition of motion symbols

An interactive loop between motion recognition and motion generation is a fundamental mechanism for humans and humanoid robots. We have been developing an intelligent framework for motion recognition and generation based on symbolizing motion primitives. The motion primitives are encoded into Hidden Markov Models (HMMs), which we call “motion symbols”. However, to determine the motion primitives to use as training data for the HMMs, this framework requires a manual segmentation of human motions. Essentially, a humanoid robot is expected to participate in daily life and must learn many motion symbols to adapt to various situations. For this use, manual segmentation is cumbersome and impractical for humanoid robots. In this study, we propose a novel approach to segmentation, the Real-time Unsupervised Segmentation (RUS) method, which comprises three phases. In the first phase, short human movements are encoded into feature HMMs. Seamless human motion can be converted to a sequence of these feature HMMs. In the second phase, the causality between the feature HMMs is extracted. The causality data make it possible to predict movement from observation. In the third phase, movements having a large prediction uncertainty are designated as the boundaries of motion primitives. In this way, human whole-body motion can be segmented into a sequence of motion primitives. This paper also describes an application of RUS to AUtonomous Symbolization of motion primitives (AUS). Each derived motion primitive is classified into an HMM for a motion symbol, and parameters of the HMMs are optimized by using the motion primitives as training data in competitive learning. The HMMs are gradually optimized in such a way that the HMMs can abstract similar motion primitives. We tested the RUS and AUS frameworks on captured human whole-body motions and demonstrated the validity of the proposed framework.     

机器人运动轨迹的模仿学习综述EI北大核心CSCD

作为机器人技能学习中的一个重要分支,模仿学习近年来在机器人系统中得到了广泛的应用.模仿学习能够将人类的技能以一种相对直接的方式迁移到机器人系统中,其思路是先从少量示教样本中提取相应的运动特征,然后将该特征泛化到新的情形.本文针对机器人运动轨迹的模仿学习进行综述.首先详细解释模仿学习中的技能泛化、收敛性和外插等基本问题;其次从原理上对动态运动基元、概率运动基元和核化运动基元等主要的模仿学习算法进行介绍;然后深入地讨论模仿学习中姿态和刚度矩阵的学习问题、协同和不确定性预测的问题以及人机交互中的模仿学习等若干关键问题;最后本文探讨了结合因果推理的模仿学习等几个未来的发展方向.     

Incremental Learning of Skills in a Task-Parameterized Gaussian Mixture Model

Programming by demonstration techniques facilitate the programming of robots. Some of them allow the generalization of tasks through parameters, although they require new training when trajectories different from the ones used to estimate the model need to be added. One of the ways to re-train a robot is by incremental learning, which supplies additional information of the task and does not require teaching the whole task again. The present study proposes three techniques to add trajectories to a previously estimated task-parameterized Gaussian mixture model. The first technique estimates a new model by accumulating the new trajectory and the set of trajectories generated using the previous model. The second technique permits adding to the parameters of the existent model those obtained for the new trajectories. The third one updates the model parameters by running a modified version of the Expectation-Maximization algorithm, with the information of the new trajectories. The techniques were evaluated in a simulated task and a real one, and they showed better performance than that of the existent model.     

Teaching robots to cooperate with humans in dynamic manipulation tasks based on multi-modal human-in-the-loop approach

We propose an approach to efficiently teach robots how to perform dynamic manipulation tasks in cooperation with a human partner. The approach utilises human sensorimotor learning ability where the human tutor controls the robot through a multi-modal interface to make it perform the desired task. During the tutoring, the robot simultaneously learns the action policy of the tutor and through time gains full autonomy. We demonstrate our approach by an experiment where we taught a robot how to perform a wood sawing task with a human partner using a two-person cross-cut saw. The challenge of this experiment is that it requires precise coordination of the robot’s motion and compliance according to the partner’s actions. To transfer the sawing skill from the tutor to the robot we used Locally Weighted Regression for trajectory generalisation, and adaptive oscillators for adaptation of the robot to the partner’s motion.     

Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives

Vertebrates are able to quickly adapt to new environments in a very robust, seemingly effortless way. To explain both this adaptivity and robustness, a very promising perspective in neurosciences is the modular approach to movement generation: Movements results from combinations of a finite set of stable motor primitives organized at the spinal level. In this article we apply this concept of modular generation of movements to the control of robots with a high number of degrees of freedom, an issue that is challenging notably because planning complex, multidimensional trajectories in time-varying environments is a laborious and costly process. We thus propose to decrease the complexity of the planning phase through the use of a combination of discrete and rhythmic motor primitives, leading to the decoupling of the planning phase (i.e. the choice of behavior) and the actual trajectory generation. Such implementation eases the control of, and the switch between, different behaviors by reducing the dimensionality of the high-level commands. Moreover, since the motor primitives are generated by dynamical systems, the trajectories can be smoothly modulated, either by high-level commands to change the current behavior or by sensory feedback information to adapt to environmental constraints. In order to show the generality of our approach, we apply the framework to interactive drumming and infant crawling in a humanoid robot. These experiments illustrate the simplicity of the control architecture in terms of planning, the integration of different types of feedback (vision and contact) and the capacity of autonomously switching between different behaviors (crawling and simple reaching).     

Complete Your Mobility: Linking Trajectories Across Heterogeneous Mobility Data Sources

Nowadays, human activities and movements are recorded by a variety of tools, forming different trajectory sets which are usually isolated from one another. Thus, it is very important to link different trajectories of one person in different sets to provide massive information for facilitating trajectory mining tasks. Most prior work took advantages of only one dimensional information to link trajectories and can link trajectories in a one-to-many manner (providing several candidate trajectories to link to one specific trajectory). In this paper, we propose a novel approach called one-to-one constraint trajectory linking with multi-dimensional information (OCTL) that links the corresponding trajectories of one person in different sets in a one-to-one manner. We extract multidimensional features from different trajectory datasets for corresponding relationships prediction, including spatial, temporal and spatio-temporal information, which jointly describe the relationships between trajectories. Using these features, we calculate the corresponding probabilities between trajectories in different datasets. Then, we formulate the link inference problem as a bipartite graph matching problem and employ effective methods to link one trajectory to another. Moreover, the advantages of our approach are empirically verified on two real-world trajectory sets with convincing results.     

Context-based semantical vector representations for animal trajectories

ABSTRACT

Behaviour could be expressed as a set of specific movement patterns in time. An animal's movement or trajectory could characterise its behaviours and provide information about its internal states. Recent advances in GPS-based sensor technologies led to drastic increase in volume of the data collected from animals' movements which enables researchers to analyse and model their behaviours using data-driven methods. However, having compact, discriminative, semantical and independent numerical representations of trajectories as features, is essential for employing the most of available off-the-shelf machine learning and deep learning techniques. Inspired by language processing, the approach presented in this study utilizes Skip-gram model to create contextual vector embeddings or representations of key-points in animal trajectories to be used as input features. Here, a key-point is defined as a location which represents a trajectory segment. It is assumed that these key-points encapsulate contextual information which is attributed to a certain behaviour or specific group of animals with similar behavioural features. So, the vector embeddings could be interpreted as contextual semantical representations of trajectory key-points independent of their spatial coordinates. With these representations, it would be possible to predict likelihood of preceding or subsequent key-points given a context or an internal state, or vice versa. To test this hypothesis, an experiment was conducted on birds' trajectories logged from a seabird species, Streaked Shearwater (Calonectris leucomelas). In this experiment, vector representations of the key-points in birds' trajectories were constructed and optimized using candidate sampling. The experimental results showcased the utility of these vector embeddings in both exploration of Streaked Shearwater trajectory data and improvement of gender-based trajectory classification. In summary, the proposed method provided a novel approach for numerical representation of animal trajectories and, it was illustrated to be semantically more explanatory for analysis as well as being more informative as features for modelling of animal movement data.     

Trajectory generation and control of a knee exoskeleton based on dynamic movement primitives for sit-to-stand assistance

This paper presents a novel control approach for a knee exoskeleton to assist individuals with lower extremity weakness during sit-to-stand motion. The proposed method consists of a trajectory generator and an impedance controller. The trajectory generator uses a library of sample trajectories as the training data and the initial joint angles as the input to predict the user’s intended sit-to-stand trajectory. Utilizing the dynamic movement primitives theory, the trajectory generator represents the predicted trajectory in a time-normalized and rather a flexible framework. The impedance controller is then employed to provide assistance by guiding the knee joint to move along the predicted trajectory. Moreover, the human-exoskeleton interaction force is used as the feedback for on-line adaptation of the trajectory speed. The proposed control strategy was tested on a healthy adult who wore the knee exoskeleton on his leg. The subject was asked to perform a number of sit-to-stand movements from different sitting positions. Next, the measured data and the inverse dynamic model of the human-exoskeleton system are used to calculate the knee power and torque profiles. The results reveal that average muscle activity decreases when the subject is assisted by the exoskeleton.     

Parametric Planning for Multiple Cooperative Robots

A novel planning strategy, parametric planning, is proposed to negotiate the task-oriented object manipulation of multiple coordinated robots. The approach provides an advantage to improve flexibility of robotic cooperation, in which the desired trajectories in Cartesian space derived from task requirements are converted into the trajectories of robots in joint space for a fixed-coordinated multi-robot system. For this purpose, a parametric cooperative index matrix is introduced to handle the relationship of the input desired Cartesian trajectories and the position of robots. A case study of 2-dimension object-motion trajectory tracking using four robots is presented in the end. It proved that the proposed approach effectively delivers trajectory task requirements to the joint trajectories of robots.     

Co-manipulation with a library of virtual guiding fixtures

Virtual guiding fixtures constrain the movements of a robot to task-relevant trajectories, and have been successfully applied to, for instance, surgical and manufacturing tasks. Whereas previous work has considered guiding fixtures for single tasks, in this paper we propose a library of guiding fixtures for multiple tasks, and propose methods for (1) creating and adding guides based on machine learning; (2) selecting guides on-line based on probabilistic implementation of guiding fixtures; (3) refining existing guides based on an incremental learning method. We demonstrate in an industrial task that a library of guiding fixtures provides an intuitive haptic interface for joint human–robot completion of tasks, and improves performance in terms of task execution time, mental workload and errors.     

Walking in the resonance with the COMAN robot with trajectories based on human kinematic motion primitives (kMPs)

Research in humanoid robotics aims to develop autonomous systems that are able to assist humans in the performance of everyday tasks. Part of the robotics community claims that the best solution to guarantee the maximum adaptability of robots to the majority of human tasks is mimicry. Based on this premise both the structure of the human body and human behavior have been the focus of studies, with the aim of imitating and reproducing on robotic systems the results of millennia of human evolution. The research presented in this paper aims (i) at transferring the features of human locomotion to the COmpliant huMANoid (COMAN) robot, by means of kinematic motion primitives (kMPs) extracted from human subjects, and (ii) at improving the energetic performance of the walk of COMAN by exploiting its intrinsic compliance: it will be shown that, when the robot is walking at a gait frequency that is close to one of the main resonance frequencies of the mechanism, the springs contribute to tracking the human-like kMPs-based trajectories imposed, providing at the right time about 15 % of the energy required for locomotion, and that was previously stored.     

Robot Catching: Towards Engaging Human-Humanoid Interaction

Our focus is on creating interesting and human-like behaviors for humanoid robots and virtual characters. Interactive behaviors are especially engaging. They are also challenging, as they necessitate finding satisfactory realtime solutions for complex systems such as the 30-degree-of-freedom humanoid robot in our laboratory. Here we describe a catching behavior between a person and a robot. We generate ball-hand impact predictions based on the flight of the ball, and human-like motion trajectories to move the hand to the catch position. We use a dynamical systems approach to produce the motion trajectories where new movements are generated from motion primitives as they are needed.     

模仿学习示教轨迹自动分割方法的研究进展

符号表达的模仿学习是共融机器人提高其智能性的一条便捷、可行的途径,也为解决复杂、多步骤任务的学习问题提供了一个切实可行的解决方案,而对示教轨迹进行自动分割并获取其基本动作是成功应用这种学习方式的前提条件.鉴于此,首先,在介绍符号表示的模仿学习的基础上,分析该种学习方式对自动分割方法的具体要求;然后,按照示教任务先验知识的有无将其分为两大类并详细地介绍每类所含的典型分割方法;最后,对上述轨迹分割方法进行对比分析与总结,并展望示教轨迹自动分割方法未来的发展趋势.     

Dynamically-Stable Motion Planning for Humanoid Robots

We present an approach to path planning for humanoid robots that computes dynamically-stable, collision-free trajectories from full-body posture goals. Given a geometric model of the environment and a statically-stable desired posture, we search the configuration space of the robot for a collision-free path that simultaneously satisfies dynamic balance constraints. We adapt existing randomized path planning techniques by imposing balance constraints on incremental search motions in order to maintain the overall dynamic stability of the final path. A dynamics filtering function that constrains the ZMP (zero moment point) trajectory is used as a post-processing step to transform statically-stable, collision-free paths into dynamically-stable, collision-free trajectories for the entire body. Although we have focused our experiments on biped robots with a humanoid shape, the method generally applies to any robot subject to balance constraints (legged or not). The algorithm is presented along with computed examples using both simulated and real humanoid robots.     

Algorithms for rough terrain trajectory planning

This paper deals with motion planning on rough terrain for mobile robots. The aim is to develop efficient algorithms, suitable for various types of robots. On rough terrain, the planned trajectory must verify several validity constraints : stability of the robot, mechanical limits and collision avoidance with the ground. Our approach relies on a static and kinematic model of the robot. Efficient geometric algorithms have been developed, taking advantage of each vehicle's specificities. Motion planning relies on an incremental search in the discretized configuration space and uses efficient heuristics based on terrain characteristic to limit the size of the search space. Simulation results present trajectories planned in a few seconds. The second part takes into account uncertainties to improve trajectory robustness: uncertainties on the terrain model and the position of the robot. The adaptation of the previous algorithms allows us to find robust trajectories, without any excessive time increase.