View Chapter

Chapter 13 — Behavior-Based Systems

François Michaud and Monica Nicolescu

Nature is filled with examples of autonomous creatures capable of dealing with the diversity, unpredictability, and rapidly changing conditions of the real world. Such creatures must make decisions and take actions based on incomplete perception, time constraints, limited knowledge about the world, cognition, reasoning and physical capabilities, in uncontrolled conditions and with very limited cues about the intent of others. Consequently, one way of evaluating intelligence is based on the creature’s ability to make the most of what it has available to handle the complexities of the real world. The main objective of this chapter is to explain behavior-based systems and their use in autonomous control problems and applications. The chapter is organized as follows. Section 13.1 overviews robot control, introducing behavior-based systems in relation to other established approaches to robot control. Section 13.2 follows by outlining the basic principles of behavior-based systems that make them distinct from other types of robot control architectures. The concept of basis behaviors, the means of modularizing behavior-based systems, is presented in Sect. 13.3. Section 13.4 describes how behaviors are used as building blocks for creating representations for use by behavior-based systems, enabling the robot to reason about the world and about itself in that world. Section 13.5 presents several different classes of learning methods for behavior-based systems, validated on single-robot and multirobot systems. Section 13.6 provides an overview of various robotics problems and application domains that have successfully been addressed or are currently being studied with behavior-based control. Finally, Sect. 13.7 concludes the chapter.

Experience-based learning of high-level task representations: Demonstration

Author  Monica Nicolescu

Video ID : 27

This is a video recorded in early 2000s, showing a Pioneer robot learning to visit a number of targets in a certain order - the human demonstration stage. The robot execution stage is also shown in a related video in this chapter. References: 1. M. Nicolescu, M.J. Mataric: Experience-based learning of task representations from human-robot interaction, Proc. IEEE Int. Symp. Comput. Intell. Robot. Autom. Banff (2001), pp. 463-468; 2. M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

Experience-based learning of high-level task representations: Reproduction

Author  Monica Nicolescu

Video ID : 28

This is a video recorded in early 2000s, showing a Pioneer robot visiting a number of targets in a certain order based on a demonstration provided by a human user. The robot training stage is also shown in a related video in this chapter. References: 1. M. Nicolescu, M.J. Mataric: Experience-based learning of task representations from human-robot interaction, Proc. IEEE Int. Symp. Comput. Intell. Robot. Autom. , Banff (2001), pp. 463-468; 2. M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

Experience-based learning of high-level task representations: Demonstration (2)

Author  Monica Nicolescu

Video ID : 30

This is a video recorded in early 2000s, showing a Pioneer robot learning to slalom around a number of targets in a certain order - the human demonstration stage. The robot execution stage is also shown in a related video in this chapter. References: 1. M. Nicolescu, M.J. Mataric: Experience-based learning of task representations from human-robot interaction, Proc. IEEE Int. Symp. Comput. Intell. Robot. Autom. , Banff (2001), pp. 463-468; 2. M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

Experience-based learning of high-level task representations: Reproduction (2)

Author  Monica Nicolescu

Video ID : 31

This is a video recorded in early 2000s, showing a Pioneer robot learning to visit a number of targets in a certain order - the robot execution stage. The robot training stage is also shown in a related video in this chapter. References: 1. M. Nicolescu, M.J. Mataric: Experience-based learning of task representations from human-robot interaction, Proc. IEEE Int. Symp. Comput. Intell. Robot. Autom. , Banff (2001), pp. 463-468; 2. M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

Experience-based learning of high-level task representations: Demonstration (3)

Author  Monica Nicolescu

Video ID : 32

This is a video recorded in early 2000s, showing a Pioneer robot learning to traverse "gates" and move objects from a source place to a destination - the human demonstration stage. The robot execution stage is also shown in a related video in this chapter. Reference: M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

Experience-based learning of high-level task representations: Reproduction (3)

Author  Monica Nicolescu

Video ID : 33

This is a video recorded in early 2000s, showing a Pioneer robot learning to traverse "gates" and move objects from a source place to a destination - the robot is reproducing the learned task. The robot training stage is also shown in a related video in this chapter. Reference: M. Nicolescu, M.J. Mataric: Learning and interacting in human-robot domains, IEEE Trans. Syst. Man Cybernet. A31(5), 419-430 (2001)

The Nerd Herd

Author  Maja J. Mataric

Video ID : 34

This is a video showing the work done in the early 1990s with the Nerd Herd used as a multirobot behavior-based system. Reference: M.J. Matarić: Designing and understanding adaptive group behavior, Adapt. Behav. 4(1), 50–81 (1995)

Toto

Author  Maja J. Mataric

Video ID : 35

This is a video of the work done early 1990, showing Toto which introduced the use of distributed representation into behavior-based systems. Reference: M.J. Matarić: Integration of representation into goal-driven behavior-based robots, IEEE Trans. Robot. Autom. 8(3), 304–312 (1992)

SpartacUS

Author  François Michaud

Video ID : 417

AAAI 2005 Robot Challenge entry from the Université de Sherbrooke, named Spartacus, using MBA (motivated behavioral architecture) to enable a robot to participate at the conference as a regular attendee. Reference: F. Michaud, C. Côté, D. Létourneau, Y. Brosseau, J.-M. Valin, É. Beaudry, C. Raïevsky, A. Ponchon, P. Moisan, P. Lepage, Y. Morin, F. Gagnon, P. Giguère, M.-A. Roux, S. Caron, P. Frenette, F. Kabanza: Spartacus attending the 2005 AAAI Conference, Auton. Robot. 12(2), 211–222 (2007)

Natural interaction design of a humanoid robot

Author  François Michaud

Video ID : 418

Demonstration of the use of HBBA, hybrid behavior-based architecture, to implement three interactional capabilities on IRL-1. Reference: F. Ferland, D. Létourneau, M.-A. Legault, M. Lauria, F. Michaud: Natural interaction design of a humanoid robot, J. Human-Robot Interact. 1(2), 118-134 (2012)