Andrew Nelson

About

Andrew Nelson is a robotics researcher whose work sits at the intersection of evolutionary computation, autonomous systems, and mobile robot reliability. He is best known for his influential 2008 survey "Fitness Functions in Evolutionary Robotics," which has accumulated 260 citations and remains a foundational reference for researchers designing and evaluating evolutionary robotics systems. Much of Nelson's research explores how artificial evolution can be harnessed to automatically develop neural network controllers for mobile robots, with a particular focus on competitive fitness functions that drive the emergence of sophisticated team-based game-playing behaviors. His repeated investigation of intra-population competitive selection reflects a sustained effort to solve one of evolutionary robotics' core challenges: defining meaningful performance metrics without hand-crafting task-specific rewards. Beyond controller synthesis, Nelson has contributed to the practical side of field robotics, most notably through his analysis of mobile robot failures in hazardous real-world scenarios—work that highlights critical reliability constraints facing robots deployed in mine clearing and urban search-and-rescue operations. His colony-based robot test beds, integrating vision sensing with evolved controllers, further demonstrate a commitment to bridging simulation and physical hardware. With over 550 cumulative citations, Nelson's body of work has meaningfully shaped both the theoretical foundations and engineering practice of evolutionary and behavioral robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Fitness functions in evolutionary robotics: A survey and analysis

   260 citations · 2008
2. 2
   Follow-up analysis of mobile robot failures

   116 citations · 2004
3. 3
   Evolution of neural controllers for competitive game playing with teams of mobile robots

   56 citations · 2004
4. 4
   Maze exploration behaviors using an integrated evolutionary robotics environment

   51 citations · 2004
5. 5
   Using direct competition to select for competent controllers in evolutionary robotics

   13 citations · 2006
6. 6
   A colony of robots using vision sensing and evolved neural controllers

   12 citations · 2004
7. 7
   Evolution of complex autonomous robot behaviors using competitive fitness

   12 citations · 2004
8. 8
   Competitive relative performance evaluation of neural controllers for competitive game playing with teams of real mobile robots

   12 citations · 2002
9. 9
   Competitive Relative Performance and Fitness Selection for Evolutionary Robotics

   11 citations · 2003
10. 10
    Incorporation of MATLAB into a distributed behavioral robotics architecture

    11 citations · 2005

Key Collaborators

Contact & Links