author : Rodney A. Brooks

Contents

• Horst Hendricks-Jansen. In Praise of Interactive Emergence, Or Why Explanations Don't Have to Wait for Implementation. 1996

Using situated robotics to help explain human intentional behaviour and thought

• Peter Godfrey-Smith. Spencer and Dewey on Life and Mind. 1996

• Katsunori Shimohara. Evolutionary Systems for Brain Communications---Towards an Artificial Brain. 1994

• Luc Steels. Emergent Functionality in Robotic Agents through On-Line Evolution. 1994

• Demetri Terzopoulos, Xiaoyuan Tu, Radek Grzeszczuk. Artificial Fishes with Autonomous Locomotion, Perception, Behavior, and Learning in a Simulated Physical World. 1994

• Karl Sims. Evolving 3D Morphology and Behavior by Competition. 1994

• David H. Ackley, Michael L. Littman. Altruism in the Evolution of Communication. 1994

• Hiroaki Kitano. Evolution of Metabolism for Morphogenesis. 1994

• Craig W. Reynolds. Competition, Coevolution and the Game of Tag. 1994

• Gene Levinson. Crossovers Generate Non-Random Recombinants under Darwinian Selection. 1994

• Jan Paredis. Steps Towards Co-Evolutionary Classification Neural Networks. 1994

• Wolfgang Banzhaf. Self-Organisation in a System of Binary Strings. 1994

• Irenaeus J. A. te Boekhorst, Paulien Hogeweg. Effects of Tree Size on Travelband Formation in Orang-Utans: Data Analysis Suggested by a Model Study. 1994

• Jeffrey O. Kephart. A Biologically Inspired Immune System for Computers. 1994

• Yukihiko Toquenaga, Isamu Kajitani, Tsutomu Hoshino. Egrets of a Feather Flock Together. 1994

• Carlo C. Maley. A Model of the Effects of Dispersal Distance on the Evolution of Virulence in Parasites. 1994

• John Batali. Innate Biases and Critical Periods: Combining Evolution and Learning in the Acquisition of Syntax. 1994

• Kazuo Hosokawa, Isao Shimoyama, Hirofumi Miura. Dynamics of Self-Assembling Systems---Analogy with Chemical Kinetics. 1994

• Ralph Beckers, Owen E. Holland, Jean-Louis Deneubourg. From Local Actions to Global Tasks: Stigmergy and Collective Robotics. 1994

• Stefano Nolfi, Dario Floreano, Orazio Miglino, Francesco Mondada. How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics. 1994

• Michael Patrick Johnson, Pattie Maes, Trevor Darrell. Evolving Visual Routines. 1994

• Filippo Menczer, Richard K. Belew. Evolving Sensors in Environments of Controlled Complexity. 1994

• Kai Nagel, Steen Rasmussen. Traffic at the Edge of Chaos. 1994

• James F. Lynch. A Phase Transition in Random Boolean Networks. 1994

• Frank Dellaert, Randall D. Beer. Toward an Evolvable Model of Development for Autonomous Agent Synthesis. 1994

• Mark A. Bedau, Alan Bahm. Bifurcation Structure in Diversity Dynamics. 1994

• Christoph Adami. On Modelling Life. 1994

• Robert M. French, Adam Messinger. Genes, Phenes and the Baldwin Effect: Learning and Evolution in a Simulated Population. 1994

• Kurt Thearling, Thomas S. Ray. Evolving Multi-Cellular Artificial Life. 1994

• Kazuhiro Saitou, Mark J. Jakiela. Meshing of Engineering Domains by Meitotic Cell Division. 1994

• Hiroaki Inayoshi. Simulating Natural Spacing Patterns of Insect Bristles Using a Network of Interacting Celloids. 1994

• Lijia Zhou, Stan Franklin. Character Recognition Agents. 1994

• Eric W. Bonabeau, Guy Theraulaz, Eric Arpin, Emmanuel Sardet. The Building Behavior of Lattice Swarms. 1994

• Jari Vaario. Modeling Adaptive Self-Organization. 1994

• Jessica K. Hodgins, David C. Brogan. Robot Herds: Group Behaviors for Systems with Significant Dynamics. 1994

• Michael de la Maza, Deniz Yuret. A Futures Market Simulation with Non-Rational Participants. 1994

• Tatsuo Unemi, Masahiro Nagayoshi, Nobumasa Hirayama, Toshiaki Nade, Kiyoshi Yano, Yasuhiro Masujima. Evolutionary Differentiation of Learning Abilities---A Case Study on Optimizing Parameter Values in Q-Learning by a Genetic Algorithm. 1994

• Steve Bankes. Exploring the Foundations of Artificial Societies: Experiments in Evolving Solutions to Iterated N-Player Prisoner's Dilemma. 1994

• John Batali, Philip Kitcher. Evolutionary Dynamics of Altruistic Behavior in Optional and Compulsory Versions of the Iterated Prisoner's Dilemma. 1994

• Michael Oliphant. Evolving Cooperation in the Non-Iterated Prisoner's Dilemma: The Importance of Spatial Organization. 1994

• Peter J. Angeline. An Alternate Interpretation of the Iterated Prisoner's Dilemma and the Evolution of Non-Mutual Cooperation. 1994

• Hirofumi Doi, Ken-nosuke Wada, Mitsuru Furusawa. Asymmetric Mutations Due to Semiconservative DNA Replication: Double-Stranded DNA Type Genetic Algorithms. 1994

• P. Marchal, C. Piguet, Daniel Mange, Andre Stauffer, S. Durand. Embryological Development on Silicon. 1994

• Hitoshi Hemmi, Jun'ichi Mizoguchi, Katsunori Shimohara. Development and Evolution of Hardware Behaviors. 1994

• Christoph Adami, C. Titus Brown. Evolutionary Learning in the 2D Artificial Life System "Avida". 1994

• Hugues Bersini, Vincent Detours. Asynchrony Induces Stability in Cellular Automata Based Models. 1994

• Murray Shanahan. Evolutionary Automata. 1994

• Moshe Sipper. Non-Uniform Cellular Automata: Evolution in Rule Space and Formation of Complex Structures. 1994

• James V. Stone. Evolutionary Robots: Our Hands in Their Brains?. 1994

• Alvaro Moreno, Arantza Etxeberria, Jon Umerez. Universality Without Matter?. 1994

• Vince Darley. Emergent Phenomena and Complexity. 1994

• Markus F. Peschl. Autonomy vs. Environmental Dependency in Neural Knowledge Representation. 1994

• Takuya Saruwatari, Yukihiko Toquenaga, Tsutomu Hoshino. Adiversity: Stepping Up Trophic Levels. 1994

• Nicholas Gessler. Artificial Culture. 1994

• Jeffrey Ventrella. Explorations in the Emergence of Morphology and Locomotion Behavior in Animated Characters. 1994

• Alun Rhys Jones, Adrian J. West. An Instance of a Parasitic Replicator. 1994

In the mid 1980s AI robots seemed to be going nowhere. Robots placed in carefully sanitised highly artificial environments, with only a few easily seen stationary geometric obstacles, nevertheless spent forever observing, building models and planning before they moved an inch. The only improvements occurring seemed to be due to rapidly increasing computing power, rather than advances in the underlying mechanisms and theory.

Rodney Brooks decided it was time for a radical rethink of the entire approach. No more "cheating" by making unrealistic assumptions about the environment and the robots sensors -- instead require the robot to interact with the real world in real time. No more careful planning -- instead try building the simplest possible behaviours and, only once they are working, incrementally add more sophisticated ones. No more internal model building -- instead use the real world as its own model. And avoid the potential infinite regress of symbolic meaning by being fully grounded in the real world. Do all this and watch "intelligence" emerge as an interaction with the complex world, just as it has in reality. (But don't keep too close to evolution -- it uses blind chance, not design -- and has no purpose, no goal. It should be possible to design efficient useful behaviours.) Braitenberg's vehicles did this in theory -- how would it work in practice?

Brooks developed the subsumption architecture, where higher layers of behaviour subsume lower ones as and when appropriate. Start off with the simplest underlying behaviour -- avoid -- that stops the robot running into obstacles, and makes it dodge moving ones. Overlay a more complex one -- wander -- which adds random movement, but doesn't have to worry about avoiding things: that's already been taken care of. Then add another one -- explore -- to make the wandering behaviour less random. Then add another one -- map -- so the robot can revisit previously explored places (but keeping the map highly distributed, and using it to navigate without planning a route). And so on.

The approach was a stunning success, although not without its detractors. In a very short space of time -- only a few years -- Brooks and his team at MIT had small autonomous robots scuttling around their unmodified cluttered office space full of moving obstacles (people), acting and reacting in real time, using highly distributed and very simple control circuits to perform apparently complex and intelligent tasks.

This book collects together six of Brooks' papers from the late 1980s and early 1990s, with a short introduction to each, describing and explaining the subsumption approach, and rebutting the critics. Because it is a collection, there is some overlap and repetition. But the papers are lucidly written, and give a clear account of the state of the subsumption art at the turn of the last decade. The last paper also outlines several fascinating and exciting research topics for taking the field further forward.

Given that rapid progress ten years ago, now I want to know, what happened in the 1990s? How did those research topics pan out? What are the little critters getting up to now? Did the approach scale up, or hit some new obstacles? Is there a follow-up volume? What doesn't this book have a postscript?

Contents:

• A Robust Layered Control System for a Mobile Robot. IEEE Journal of Robotics and Automation, RA-2, 14-23, April 1986.
• A Robot That Walks: Emergent Behaviors from a Carefully Evolved Network. Neural Computation, 1:2, 253-262, Summer 1989.
• Learning a Distributed Map Representation Based on Navigation Behaviors. Proceedings of the 1990 USA-Japan Symposium on Flexible Automation, Kyoto, Japan, 499-506.
• New Approaches to Robotics. Science, 253, 1227-1232. 1991
• Intelligence without Representation. Artificial Intelligence Journal, 47, 1139-160. 1991 (originally written 1987)
• Planning Is Just a Way of Avoiding Figuring Out What to Do Next. MIT Artificial Intelligence Laboratory, Working Paper 303, September 1987
• Elephants Don't Play Chess. Robotics and Autonomous Systems, 6, 3-15. 1990
• Intelligence without Reason. Proceedings of the 1991 Joint Conference on Artificial Intelligence, 569-595.

This is Brooks' take on the science of intelligent robots, and could be considered as a "pop science" version of Cambrian Intelligence, also bringing us more up to date on what has been happening since the early 1990s. Brooks bases his approach on the subsumption architectures, a situated, embodied, "bottom-up" approach to intelligent behaviour, as opposed to Good Old-Fashioned AI's symbolic reasoning top-down approach. It also serves as Brooks' riposte to Moravec's book of the same name. Whilst expressing the greatest respect for Moravec, Brooks emphatically disagrees with his approach:

Some problems seem to be fundamentally harder than others to solve, and it's not the ones AI researchers have been concentrating on:

In fact, it's the everyday problems: movement, navigation, recognising and manipulating things in a complex noisy environment, that have posed the main challenges.

As well as castigating the GOFAIers, Brooks also lays into those carbon chauvinists who deny that "mere machines" could ever be intelligent or have real emotions, but rather claim that something extra is needed. He dismisses the circular "arguments" against "mere machines" of people like Penrose and Searle, identifying them as "tribalistic" arguments of people who can't bear to give up the idea that we are somehow special, somehow other.

(However, this dismissal seems to ridicule the use of ridicule.) He claims an existence proof that machines can have emotions, because we are machines. He does have the feeling that there is something currently missing from our descriptions, which he calls "the juice", and cheerfully admits he has no evidence for this claim. However, he does not believe that this is necessarily anything new, just something we haven't recognised yet, and is not something that we couldn't build into our machines.

The argument is interspersed with a few wry anecdotes from his career:

So what has Brooks been up to more recently? It seems one of the ways he has branched out is to make commercial robots. He too promises us the house cleaning robot soon [still waiting!], but his main foray seems to have been to sneak these critters into our homes in a friendlier way, as toys. This has required getting to grips with production engineering and marketing.

He moves on to talk about the future. The first step is interesting: he suggests that the first major use of domestic robots might be to provide us with telepresence, providing us with robots that we control, instruct, and guide around our houses via a high-level Web interface. Don't worry about providing the robot with those difficult higher levels of reasoning and intelligence, just use the subsumption architecture to provide the low level motor controls, allowing the "driver" to issue higher level commands. He weaves some interesting scenarios in this area.

Brooks then moves on to the further future, by way of artificial retinas, to full cyborg enhancements, including more intelligence "in your head". Some of his ideas echo Andy Clark's notions here. But I think this may again be far harder than is thought. For example, he talks of augmenting memory so that the answers are "just there":

When I read this, I thought "speak for yourself!" When I think of a telephone number, I do get a visual image of the digits. Moreover, I have no idea how else I could possibly think about a number. (Except for small numbers, where I get a visual image of something more like a dice face pattern.) Brooks' mental representations clearly are very different from mine. If we all have internal representations that differ so dramatically, there may be no one single technology that provides the promised augmentation. But it's going to be fun getting there, and I suspect that Brooks' approach has a lot to offer.

A quick overview of various subsumption-architecture robots, then a description of planetary exploration using lots of small simple cheap expendable autonomous robots, rather than one big expensive mission-critical one