Brooks R.: Building Brains for Bodies. (A. I. Memo No. 1439), MIT AI Lab, Cambridge, Mass., 1993  Home/Search   Document Details and Download   Summary   Related Articles   Check

....importantinthiscase. In other applications, it maywell become significant. Actuator Design 5.1 Introduction This chapter describes the build of a series elastic actuator. The specification for the actuator was determined by its eventual application as part of the arm for the humanoid robot Cog[7]. This application is described in Chapter 7. Figure 5 1 shows a photograph of the final actuator design. It consists of an electric motor and a spring instrumented with strain gauges. The actuator has a maximum output torque of 4Nm. The following sections of this chapter describe in detail the ....

....of the motor is taken into account. The actuator behaves well at low frequencies, and the spring like behaviour is very clear at high frequencies. Applications 7. 1 Cog Series elastic actuators similar to that described in this thesis are being used for the arms of the humanoid robot Cog [7]. The robot will interact with humans and perform human like tasks, so it is important that its arms are safe. The arms must not be damaged by unexpected collisions, nor must it damage its operator The actuators are being used to give the arm natural compliance which will aid it in performing ....

Brooks, R. A., and Stein, L. A., "Building brains for bodies", to appear in Autonomous Robots, (1:1), 1994.

.... syst293 explo itofi posit n const aint t obt in coordinatn mult29 degree of freedom motA n(tM ning a crank) and exploit3 t3 force intfiA3 #=fiS bet ween tn arms and object t o perform rhyt43= manipulat ion (playing wit a Slinky t y) The systM is implement ed ont3 arms oft he humanoid robot Cog [2], which is shown in Figure 1. This approach was inspired byt he work of Greene [4] and also from considerat ion of how humans movetMM arms [1] Similar approaches using neural oscillat rs have beent ken by ot33 researchers [5, 15] di#ering in complexit y oft3 scheme, andt he use in legsrat hert ....

....oftG oscillat rs in tfi ee di#erent sit tfi ns, indicatic howt hey provide useful behavior. Conclusions and suggest ions for furtfi4 work are included at t he end oft he paper. 2 TheA1 and Oscillators wo six degree of freedom arms used intfi4 work are mount ed ont he humanoid robot Cog [2] (shown in Figure 1. The arms are especially designed t intfi act st ably and robus ts wit unst uct4 ed environment s. They are light weight and use series elast ic act uat ors at every joint [12] which provide low noise force cont ol, shock t lerance and st ble intfi act= n wit passive ....

R. A. Brooks and L. A. Stein. Building brains for bodies. Autonomous Robots, 1(1):7--25, 1994.

....the sensorimotor space, starting off with seemingly random, spontaneous movements. The results presented in the study are of preliminary nature only. 3. Developmental robotics: existing theories Early theorization of developmental robotics can be traced back to Brooks [10] and Brooks and Stein [53]. Sandini et al. 54] were among the first to recognize how crucial it is to take into account development if we are off to understand human intelligence. They called their approach Developmental Engineering. As in the engineering tradition of building things, it was directed toward the definition ....

R.A. Brooks and L.A. Stein. Building brains for bodies. Autonomous Robots, 1(1):7--25, 1994.

....seriously tried to couple human like cognitive processes to these systems methodologically. Cog At the MIT Artificial Intelligence Laboratory, a research group headed by professors Rodney A. Brooks and Lynn Andrea. Stein is currently developing an integrated phys ical humanoid robot named Cog [3] shown in Figure 2 1. This systelll will include 2.1. MOTIVATION AND RELATED WORK vision, sound input and output, and dextrous manipulation all controlled by a con tinuously operating parallel MIMD computer as the brain. The processors are 16Mhz Motorola 68332s in standard boards which plug 16 ....

Brooks, Rodney A., and Stein, Lynn A., "Building Brains for Bodies", A.I. Memo No. 1,139, Cambridge, MA. 1993.

....is reminiscent of behaviours observed in real animals, such as ants following a chemical trail. 4 Maze Solving Much of the behaviour of a real world situated agent is derived from its ability to exploit the physical characteristics of its environment through the agentenvironment feedback loop [6]. Exploitation of the turning bias as a way to relocate the wind stream is one example of this. Location of a wind source through the dynamic interaction of the air flow, hair sensors and mobile base is another. We were interested in testing these properties in a more complex and challenging ....

R. Brooks and L. Steen "Building brains for bodies ", MIT AI Lab memo 1439, 1993.

....Behavior Language[1] is a parallel programming language for describing systems that react to the real world. Howerver, BL is not as powerful as generic languages like C or Common Lisp for describing various systems because it was developed for designing a network of simpler processes(AFSM s)[3]. In BL you cannot define a complex function or data structures like ordinary programming languages. Therefore the developing environment in BL lacks a variety of describable systems. Furthermore, the BL programing environment was not based on an appropriate computational model for dynamical ....

R.A.Brooks and L.A.Stein, "Building Brain for Bodies" Autonomous Robots, Vol. 1, pp. 7-25, 1994.

....in fixed simulated bipeds. The strong focus on control has left a second avenue, that of morphology enhancements leading to large performance increases in active walking, relatively unexplored. In recent times, advances in Embodied AI have increasingly stressed the importance of the robot body [2] and morphological parameters, such as mechanical structure and sensor and actuator placements, which greatly influence the performance of a robot [15] More significantly, work in passive dynamic walking by McGeer[14] Collins et al. 3] and Goswami et al. 8] have shown that morphology is all ....

R. A. Brooks and L. A. Stein. Building brains for bodies. Autonomous Robots, 1(1):7--25, 1994.

.... problems, including robot soccer (Asada, Uchibe, Noda, Tawaratsumida Hosoda 1994, Werger 1999) coordinated movement (Matari c 1995, Parker 1998, Balch Hybinette 2000) cooperative box pushing (Kube 1992, Krieger, Billeter Keller 2000, Matari c Gerkey 2000) and even humanoid control (Brooks Stein 1994, Scassellati 2000, Jenkins, Matari c Weber 2000) In this paper we discuss in detail how using the behavior substrate can be conducive to learning, focusing on multi robot learning of control policies, models, and new behaviors. 4 What Can Be Learned With Behaviors The classical goal of ....

Brooks, R. A. & Stein, L. A. (1994), `Building Brains for Bodies', Autonomous Robots 1, 7--25.

.... such as learning (See Chapter 18 for a survey that analyses this question) emerge out of the local interactions of simple components Only attempts at practically realizing higher level intelligence can provide answers to these questions, as several projects on humanoid robots, such as Cog (Brooks and Stein, 1994), intend to do. This attempt has led to a second shift in viewpoint, from behaviour based to cognitive robotics (Brooks, 1997) that has different concerns at many levels. Early behaviour based AI was too much of a reaction against deliberative planning systems, and therefore remained to a great ....

Brooks, R.A. & Stein, L.A. (1994). Building brains for bodies, Autonomous Robots, 1(1): 7--25.

....locomotion: Fukuda et al. [6] employed a dynamic simulator; Reil and Husbands [18] employed a three dimensional physics based simulator. However, in all of these approaches, little or no consideration was paid to the mechanical construction of the agent or robot. Alternatively, Brooks and Stein [3] and Pfeifer and Scheier [17] have pointed to the strong interdependence between the morphology and control of an embodied agent: design decisions regarding either aspect of an agent strongly bias the resulting behaviour. One implication of this interdependence is that often, a good choice of ....

Brooks, R. A., Stein, L. A.: Building Brains for Bodies. In: Autonomous Robots 1:1 (1994) 7-25.

....for walking in a fixed simulated biped. The strong focus on control has left a second avenue, that of morphology enhancements leading to large performance increases, relatively unexplored. In recent times, advances in Embodied AI have increasingly stressed the importance of the robot body [Brooks and Stein, 1994] and morphological parameters, such as mechanical structure and sensor and actuator placements, which greatly influence the performance of a robot [Pfeifer and Scheier, 1999] More significantly, work in passive dynamic walking by [McGeer, 1990] has shown that morphology is all important in ....

R. A. Brooks and L. A. Stein. Building brains for bodies. Autonomous Robots, 1(1):7-- 25, 1994.

....that represent persistent features of the changing data from the environment. We also discuss work currently underway to allow the robot s behavior to be improved by the emergent representations. Our work builds on research from several disciplines. These include: behavior based robotics (Brooks and Stein 1994), the dynamical nature of representation and intelligence (Steels 1995, 1996) and the philosophical insights of Maturana and Varela (1980) and Clark (1997) on the self organizing nature of living systems and their coupling with their environments. Further support for our approach comes from ....

Brooks, R. and Stein, L. (1994). Building Brains for Bodies. In Autonomous Robots 1: 7-25. Boston: Kluwer Academic Publishers.

....robustness are possible using such an architecture. These would be useful in situations where a robot must autonomously adapt to its changing surroundings, for instance in unmanned space landings. Our work builds on research from several disciplines. These include: work on behavior based robotics (Brooks and Stein 1994); work on the dynamical nature of representation and intelligence (Steels 1995 and 1996) work on the organization of living systems and their coupling with an environment (Maturana and Varela 1980, Clark 1997) and work on fluid representation in the unique architectures of the Copycat family ....

Brooks, R. and Stein, L. (1994). Building Brains for Bodies. In Autonomous Robots 1: 7-25. Boston: Kluwer Academic Publishers.

....schemata are pervasive in everyday understanding of the world. These schemata are not just tied to physical interactions, either; they also cross correlated with recurrent emotional patterns and physiological patterns. Philosophers and Auto Mechanics The Cog Project was born out of these ideas [8, 12]. If even our most abstract thoughts are a product of metaphors and schemata which are themselves grounded in our bodies physical interaction with the world, then human intelligence is inseparable from the human condition. Therefore, if we want to construct a machine with a human like mind, that ....

R. Brooks and L. A. Stein. Building brains for bodies. Autonomous Robots, 1:1:7--25, 1994. 169

....have been implemented in robots designed to perform movements in specific environments. With these strategies, robots performance can be far more accurate, faster, and repeatable than humans capabilities. However, the development of a general purpose robot is still at a very primitive stage [Brooks and Stein, 1994]. In order to enhance the usability of automated systems and to build a general purpose robot, they must be designed to be more versatile. Humans are capable of generalizing movements. When one specific movement execution is learned, the acquired information transfers to movements that are ....

Brooks, R. A., and Stein, L. A. (1994) Building Brains for Bodies. Autonomous Robots, 1, pp.7--25.

No context found.

Brooks R.: Building Brains for Bodies. (A. I. Memo No. 1439), MIT AI Lab, Cambridge, Mass., 1993

No context found.

Brooks, R. and Stein, L. (1994). Building brains for bodies. Autonomous Robots, 1(1):7--25.

No context found.

Brooks R.: Building Brains for Bodies. (A. I. Memo No. 1439), MIT AI Lab, Cambridge, Mass., 1993

No context found.

Brooks, R. A. & Stein, L. A. (1994). Building Brains for Bodies. Autonomous Robots, 1(1): 5-25.

No context found.

R. A. Brooks and L. A. Stein. Building brains for bodies. Autonomous Robots, 1(1):7--25, 1994.

No context found.

Brooks, R.A. and Stein, L.A., "Building Brains for Bodies ", to appear in Autonomous Robots, (1:1), 1994.

No context found.

R.A. Brooks and L. A. Stein, "Building Brains for Bodies", Autonomous Robots, Vol. 1, No. 1, pp. 7-25, Nov. 1994.

No context found.

R.A. Brooks and L. A. Stein. Building brains for bod- ies. Autonomous Robots', 1(1):7-25, 1994.

No context found.

Brooks, R. A. and Stein, L. A. (1993) Building brains for bodies. MIT AI Memo 1439.

No context found.

Bibliography 279 Brooks, R. A., & Stein, L. A. (1993). Building Brains for Bodies (AI Memo 1439): MIT AI Laboratory.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC