View Chapter

Chapter 74 — Learning from Humans

Aude G. Billard, Sylvain Calinon and Rüdiger Dillmann

This chapter surveys the main approaches developed to date to endow robots with the ability to learn from human guidance. The field is best known as robot programming by demonstration, robot learning from/by demonstration, apprenticeship learning and imitation learning. We start with a brief historical overview of the field. We then summarize the various approaches taken to solve four main questions: when, what, who and when to imitate. We emphasize the importance of choosing well the interface and the channels used to convey the demonstrations, with an eye on interfaces providing force control and force feedback. We then review algorithmic approaches to model skills individually and as a compound and algorithms that combine learning from human guidance with reinforcement learning. We close with a look on the use of language to guide teaching and a list of open issues.

Learning compliant motion from human demonstration II

Author  Aude Billard

Video ID : 479

This video shows how the right amount of stiffness at joint level can be taught by human demonstration to allow the robot to strike a match. The robot starts with high stiffness. This leads the robot to break the match. By tapping gently on the joint that requires a decrease in stiffness, the teacher can convey the need for stiffness to decrease. The tapping is recorded using the force sensors available in each joint of the KUKA Light Weight Robot 4++ used for this purpose. Reference: K. Kronander,A. Billard: Learning compliant manipulation through kinesthetic and tactile human-robot interaction, IEEE Trans. Haptics 7(3), 367-380 (2013); doi: 10.1109/TOH.2013.54 .

Chapter 18 — Parallel Mechanisms

Jean-Pierre Merlet, Clément Gosselin and Tian Huang

This chapter presents an introduction to the kinematics and dynamics of parallel mechanisms, also referred to as parallel robots. As opposed to classical serial manipulators, the kinematic architecture of parallel robots includes closed-loop kinematic chains. As a consequence, their analysis differs considerably from that of their serial counterparts. This chapter aims at presenting the fundamental formulations and techniques used in their analysis.

CoGiRo

Author  Marc Gouttefarde

Video ID : 45

This video demonstrates a 6-DOF fully constrained 8-cable-driven robot acting in a large workspace on palletizing applications (CoGiRo robot). Reference: J. Lamaury, M. Gouttefarde: Control of a large redundantly actuated cable-suspended parallel robot, Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Karlsruhe (2013), pp. 4659-4664

Chapter 68 — Human Motion Reconstruction

Katsu Yamane and Wataru Takano

This chapter presents a set of techniques for reconstructing and understanding human motions measured using current motion capture technologies. We first review modeling and computation techniques for obtaining motion and force information from human motion data (Sect. 68.2). Here we show that kinematics and dynamics algorithms for articulated rigid bodies can be applied to human motion data processing, with help from models based on knowledge in anatomy and physiology. We then describe methods for analyzing human motions so that robots can segment and categorize different behaviors and use them as the basis for human motion understanding and communication (Sect. 68.3). These methods are based on statistical techniques widely used in linguistics. The two fields share the common goal of converting continuous and noisy signal to discrete symbols, and therefore it is natural to apply similar techniques. Finally, we introduce some application examples of human motion and models ranging from simulated human control to humanoid robot motion synthesis.

Example of muscle tensions computed from motion-capture data

Author  Katsu Yamane

Video ID : 763

This video shows an example of muscle tensions computed from motion-capture data. The muscle color changes from yellow to red as the tension increases. The blue lines represent tendons.

Chapter 23 — Biomimetic Robots

Kyu-Jin Cho and Robert Wood

Biomimetic robot designs attempt to translate biological principles into engineered systems, replacing more classical engineering solutions in order to achieve a function observed in the natural system. This chapter will focus on mechanism design for bio-inspired robots that replicate key principles from nature with novel engineering solutions. The challenges of biomimetic design include developing a deep understanding of the relevant natural system and translating this understanding into engineering design rules. This often entails the development of novel fabrication and actuation to realize the biomimetic design.

This chapter consists of four sections. In Sect. 23.1, we will define what biomimetic design entails, and contrast biomimetic robots with bio-inspired robots. In Sect. 23.2, we will discuss the fundamental components for developing a biomimetic robot. In Sect. 23.3, we will review detailed biomimetic designs that have been developed for canonical robot locomotion behaviors including flapping-wing flight, jumping, crawling, wall climbing, and swimming. In Sect. 23.4, we will discuss the enabling technologies for these biomimetic designs including material and fabrication.

RHex the parkour robot

Author  Uluc Saranli, Martin Buehler, Daniel E. Koditschek

Video ID : 400

RHex is an all-terrain walking robot that could conceivably one day climb over rubble in a rescue mission or cross the desert with environmental sensors strapped to its back. The name is pronounced "Rex" like the over-excited puppy it resembles when it is bounding over the ground; RHex is short for "robot hexapod", a name that stems from its six springy legs.

Chapter 64 — Rehabilitation and Health Care Robotics

H.F. Machiel Van der Loos, David J. Reinkensmeyer and Eugenio Guglielmelli

The field of rehabilitation robotics considers robotic systems that 1) provide therapy for persons seeking to recover their physical, social, communication, or cognitive function, and/or that 2) assist persons who have a chronic disability to accomplish activities of daily living. This chapter will discuss these two main domains and provide descriptions of the major achievements of the field over its short history and chart out the challenges to come. Specifically, after providing background information on demographics (Sect. 64.1.2) and history (Sect. 64.1.3) of the field, Sect. 64.2 describes physical therapy and exercise training robots, and Sect. 64.3 describes robotic aids for people with disabilities. Section 64.4 then presents recent advances in smart prostheses and orthoses that are related to rehabilitation robotics. Finally, Sect. 64.5 provides an overview of recent work in diagnosis and monitoring for rehabilitation as well as other health-care issues. The reader is referred to Chap. 73 for cognitive rehabilitation robotics and to Chap. 65 for robotic smart home technologies, which are often considered assistive technologies for persons with disabilities. At the conclusion of the present chapter, the reader will be familiar with the history of rehabilitation robotics and its primary accomplishments, and will understand the challenges the field may face in the future as it seeks to improve health care and the well being of persons with disabilities.

MIT Manus robotic therapy robot and other robots from the MIT group

Author  Hermano Krebs

Video ID : 496

MIT Manus is one of the first and most-widely-tested, rehabilitation-therapy robots, and is now a commercial product sold by Interactive Motion Technologies. It is a two-joint robot arm that assists and measures planar reaching movements.

Chapter 40 — Mobility and Manipulation

Oliver Brock, Jaeheung Park and Marc Toussaint

Mobile manipulation requires the integration of methodologies from all aspects of robotics. Instead of tackling each aspect in isolation,mobilemanipulation research exploits their interdependence to solve challenging problems. As a result, novel views of long-standing problems emerge. In this chapter, we present these emerging views in the areas of grasping, control, motion generation, learning, and perception. All of these areas must address the shared challenges of high-dimensionality, uncertainty, and task variability. The section on grasping and manipulation describes a trend towards actively leveraging contact and physical and dynamic interactions between hand, object, and environment. Research in control addresses the challenges of appropriately coupling mobility and manipulation. The field of motion generation increasingly blurs the boundaries between control and planning, leading to task-consistent motion in high-dimensional configuration spaces, even in dynamic and partially unknown environments. A key challenge of learning formobilemanipulation consists of identifying the appropriate priors, and we survey recent learning approaches to perception, grasping, motion, and manipulation. Finally, a discussion of promising methods in perception shows how concepts and methods from navigation and active perception are applied.

Avian-inspired grasping for quadrotor micro UAVs

Author  Justin Thomas, Joe Polin, Koushil Sreenath, Vijay Kumar

Video ID : 654

Drawing inspiration from aerial hunting by birds of prey, we design and equip a quadrotor MAV with an actuated appendage enabling grasping and object retrieval at high speeds. We develop a nonlinear dynamic model of the system, demonstrate that the system is differentially flat, plan dynamic trajectories using the flatness property, and present experimental results with pick-up velocities at 2m/s (six body lengths/s) and 3m/s (nine body lengths/s).

Chapter 11 — Robots with Flexible Elements

Alessandro De Luca and Wayne J. Book

Design issues, dynamic modeling, trajectory planning, and feedback control problems are presented for robot manipulators having components with mechanical flexibility, either concentrated at the joints or distributed along the links. The chapter is divided accordingly into two main parts. Similarities or differences between the two types of flexibility are pointed out wherever appropriate.

For robots with flexible joints, the dynamic model is derived in detail by following a Lagrangian approach and possible simplified versions are discussed. The problem of computing the nominal torques that produce a desired robot motion is then solved. Regulation and trajectory tracking tasks are addressed by means of linear and nonlinear feedback control designs.

For robots with flexible links, relevant factors that lead to the consideration of distributed flexibility are analyzed. Dynamic models are presented, based on the treatment of flexibility through lumped elements, transfer matrices, or assumed modes. Several specific issues are then highlighted, including the selection of sensors, the model order used for control design, and the generation of effective commands that reduce or eliminate residual vibrations in rest-to-rest maneuvers. Feedback control alternatives are finally discussed.

In each of the two parts of this chapter, a section is devoted to the illustration of the original references and to further readings on the subject.

Trajectory generation and control for a KUKA IR 161/60 robot

Author  Joris De Schutter

Video ID : 770

This ICRA 1992 video shows the performance obtained with two simple modifications of a standard robot controller for a KUKA IR 161/60 industrial robot, namely improved trajectory generation and control of the first joint bases on a flexible joint model. At very high velocities and accelerations, there is a significant difference between the flexible controller and a classical PID controller. A nonlinear flexible controller implemented for links 2 and 3 improves the static and dynamic accuracy of the robot. Reference: J. Swevers, D. Torfs, M. Adams, J. De Schutter, H. Van Brussel: Comparison of control algorithms for flexible joint robots implemented on a Kuka IR 161/60 industrial robot, 5th Int. Conf. Adv. Robot., Pisa (1991), pp. 120-125; doi: 10.1109/ICAR.1991.240465

Chapter 76 — Evolutionary Robotics

Stefano Nolfi, Josh Bongard, Phil Husbands and Dario Floreano

Evolutionary Robotics is a method for automatically generating artificial brains and morphologies of autonomous robots. This approach is useful both for investigating the design space of robotic applications and for testing scientific hypotheses of biological mechanisms and processes. In this chapter we provide an overview of methods and results of Evolutionary Robotics with robots of different shapes, dimensions, and operation features. We consider both simulated and physical robots with special consideration to the transfer between the two worlds.

Evolved homing walk on rough ground

Author  Phil Husbands

Video ID : 373

Evolved, simulated hexapod walks over rough terrain while homing on a beacon. This behavior was incrementally evolved with the controlling neural-network architecture which was expanding at each stage. Work done at Sussex University by Eric Vaughan.

Chapter 75 — Biologically Inspired Robotics

Fumiya Iida and Auke Jan Ijspeert

Throughout the history of robotics research, nature has been providing numerous ideas and inspirations to robotics engineers. Small insect-like robots, for example, usually make use of reflexive behaviors to avoid obstacles during locomotion, whereas large bipedal robots are designed to control complex human-like leg for climbing up and down stairs. While providing an overview of bio-inspired robotics, this chapter particularly focus on research which aims to employ robotics systems and technologies for our deeper understanding of biological systems. Unlike most of the other robotics research where researchers attempt to develop robotic applications, these types of bio-inspired robots are generally developed to test unsolved hypotheses in biological sciences. Through close collaborations between biologists and roboticists, bio-inspired robotics research contributes not only to elucidating challenging questions in nature but also to developing novel technologies for robotics applications. In this chapter, we first provide a brief historical background of this research area and then an overview of ongoing research methodologies. A few representative case studies will detail the successful instances in which robotics technologies help identifying biological hypotheses. And finally we discuss challenges and perspectives in the field.

Biologically inspired robotics (or bio-inspired robotics in short) is a very broad research area because almost all robotic systems are, in one way or the other, inspired from biological systems. Therefore, there is no clear distinction between bio-inspired robots and the others, and there is no commonly agreed definition [75.1]. For example, legged robots that walk, hop, and run are usually regarded as bio-inspired robots because many biological systems rely on legged locomotion for their survival. On the other hand, many robotics researchers implement biologicalmodels ofmotion control and navigation onto wheeled platforms, which could also be regarded as bio-inspired robots [75.2].

JenaWalker - Biped robot with biologically-inspired, bi-articular springs

Author  Fumiya Iida, Auke Ijspeertb

Video ID : 110

This video presents dynamic locomotion of a passivity-based, biped robot which contains biologically inspired bi-articular springs. The platform was developed for the purpose of understanding the roles of diverse muscle groups in human legs. A set of mechanical tension springs was incorporated to simulate muscles including bi-articular muscles which span two joints.

Chapter 9 — Force Control

Luigi Villani and Joris De Schutter

A fundamental requirement for the success of a manipulation task is the capability to handle the physical contact between a robot and the environment. Pure motion control turns out to be inadequate because the unavoidable modeling errors and uncertainties may cause a rise of the contact force, ultimately leading to an unstable behavior during the interaction, especially in the presence of rigid environments. Force feedback and force control becomes mandatory to achieve a robust and versatile behavior of a robotic system in poorly structured environments as well as safe and dependable operation in the presence of humans. This chapter starts from the analysis of indirect force control strategies, conceived to keep the contact forces limited by ensuring a suitable compliant behavior to the end effector, without requiring an accurate model of the environment. Then the problem of interaction tasks modeling is analyzed, considering both the case of a rigid environment and the case of a compliant environment. For the specification of an interaction task, natural constraints set by the task geometry and artificial constraints set by the control strategy are established, with respect to suitable task frames. This formulation is the essential premise to the synthesis of hybrid force/motion control schemes.

Experiments of spatial impedance control

Author  Fabrizio Caccavale, Ciro Natale, Bruno Siciliano, Luigi Villani

Video ID : 686

The videod results of an experimental study of impedance control schemes for a robot manipulator in contact with the environment are presented. Six-DOF interaction tasks are considered that require the implementation of a spatial impedance described in terms of both its translational and its rotational parts. Two representations of end-effector orientation are adopted, namely, Euler angles and quaternions, and the implications for the choice of different orientation displacements are discussed. The controllers are tested on an industrial robot with open-control architecture in a number of case studies. This work was published in A. Casals, A.T. de Almeida (Eds.): Experimental Robotics V, Lect. Note. Control Inform. Sci. 232 (Springer, Berlin, Heidelberg 1998)