Short works

Books : reviews

Rodney A. Brooks, Pattie Maes, eds.
Artificial Life IV: proceedings of the fourth international workshop on the synthesis and simulation of living systems, Cambridge MA.
MIT Press. 1994

(read but not reviewed)


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

Rodney A. Brooks.
Cambrian Intelligence: the early history of the new AI.
MIT Press. 1999

rating : 3.5 : worth reading
review : 26 August 2001

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.

He who deliberates fully before taking a step will spend his entire life on one foot.

-- Chinese proverb

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?


Rodney A. Brooks.
Robot: the future of flesh and machines.
Penguin. 2002

rating : 3.5 : worth reading
review : 7 July 2005

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:

p28. He has carried this conviction for more than twenty-five years, and his latest research project at Carnegie Mellon University is his umpteenth implementation of an even better three-dimensional reconstruction program. I have tried to convince him over the years that (1) animals, including humans, do not make accurate three-dimensional maps and are still able to act intelligently in the world, and that (2) once he has these maps he is going to have to do something clever with them, so perhaps it is worth thinking about that problem a little now in order to guide requirements on the characteristics of the maps. I have yet to succeed.

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

p36. Judging by the projects chosen in the early days of AI, intelligence was thought to be best characterized as the things that highly educated male scientists found challenging.

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.

p180. Like Searle's Chinese Room, there is no real argument made against a beer can computer being intelligent---mere ridicule is used. Sort of like the idea that the world can't possible be round because everybody in Australia would fall off. Ridicule does not make a valid argument. Ridicule instead of reason is a well-known refuge for tribalism.

(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:

p188. When I first expounded this theory at a workshop in Switzerland, I was forty years old. At dinner that evening a young graduate student from Oxford told me that what I had said was very interesting and that he thought a lot of people came to similar sorts of ideas when they were in the sunset of their careers.

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":

p229. When we think of our own [telephone] number, we do not conjure up a visual image of the digits. Instead, the "number," whatever that means, is 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.

Papers/Articles : reviews

Rodney A. Brooks, Anita M. Flynn. Fast, Cheap, and Out of Control: a robot invasion of the solar system. Journal of the British Interplanetary Society. 42(10). 478-485. October. 1989

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