Co-evolving Control and Morphology with LEGO Robots

نویسنده

  • Henrik Hautop Lund
چکیده

The Building Brains and Bodies approach to the design of taskfulfilling robots is introduced. In this approach, focus is on designing both controller and morphology of robots, and it thereby contrasts most research in adaptive robotics that puts emphasis on design of control exclusively. It is possible to coevolve robot control and morphology in simulation, and this work suggests that there exists important correlations between different body parameters (e.g. wheel base diameter, body size, and sensory range) in order to achieve optimal performance on specific tasks. The evolved morphology can be constructed with LEGO, and the evolved controller can be downloaded to the LEGO MINDSTORMS RCX. Hence, the experiments suggest a path towards automatic building plans for LEGO MINDSTORMS robots. Further, it is possible to manipulate the morphology in a user-guided approach of building modular LEGO robots, which allow children to construct their own robots within 10 minutes. Finally, the experiments give suggestion to new research on building blocks with processing power.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Method for Co-Evolving Morphology and Walking Pattern of Biped Humanoid Robot

In this paper, we present a method for co-evolving structures and controller of biped walking robots. Currently, biped walking humanoid robots are designed manually on trial-and-error basis. Although certain control theory exists, such as zero moment point (ZMP) compensation, these theories assume humanoid robot morphology is given in advance. Thus, engineers have to design control program for ...

متن کامل

Co-evolution of morphology and walking pattern of biped humanoid robot using evolutionary computation. Consideration of characteristic of the servomotors

In this paper, we present a method for co-evolving morphology and controller of bi-ped humanoid robots. Currently, bi-ped walking humanoid robots are designed manually on trial-and-error basis. Thus, engineers have to design control program for apriori designed morphology, neither of them shown to be optimal within a large design space. We propose evolutionary approach that co-evolves the morph...

متن کامل

Dynamic Resolution in the Co-Evolution of Morphology and Control

Evolutionary robotics is a promising approach to overcoming the limitations and biases of human designers in producing control strategies for autonomous robots. However, most work in evolutionary robotics remains solely concerned with optimizing control strategies for existing morphologies. By contrast, natural evolution, the only process that has produced intelligent agents to date, may modify...

متن کامل

The Utility of Evolving Simulated Robot Morphology Increases with Task Complexity for Object Manipulation

Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to evolve an agent's morphology along with its control in the hope that evolution will find a good coupled system. In order for embodied artificial intelligence to gain credibility within the robotics and cognitive scie...

متن کامل

LISP and LEGO MindStorms®: Perfect Together?

In this paper I explain the ongoing efforts at Villanova University to mould LEGO MindStorms into a suitable platform for college students to investigate a broad range of computer science and artificial intelligence topics within the Common Lisp programming language. This is done within a library called RCXLisp. The library has two features that distinguish it from other third-party packages an...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002