Evolutionary robotics
Topic outline
-
The course offers an introduction to evolutionary computation, its applications to neural computation, robot control, body-brain co-design, and evolutionary biology. Students are also exposed to open research topics that resort to evolutionary computation, such as self-repairing robots, self-reproducing robots, tensegrity robot control, and biohybrid robots. The course consists of ex-cathedra lectures, lab exercises with Phython, and a team project on co-evolution of robotic brains and bodies.
The course builds on foundational chapters from Floreano, D. and Mattiussi, C. (2008) Bio-inspired Artificial Intelligence. Cambridge, MA: MIT Press. In addition, several research articles describing recent research results are provided on Moodle.
Credits: 3
Thursday, 09:15-12:00
Final written exam: Friday 23 June 2023 from 15h15 to 16h15 (BC01). Bring your student ID and an ink pen (not a pencil). Books, notes, personal devices are not allowed. Students with special arrangements from SAC, please email Dario.Floreano@epfl.ch for confirmation before the exam.
Grade: 50% written exam (Multiple Choice Questions), 50% project presentation and demo
-
09:15-12:00Lecture
- Course introduction: objectives, contents, logistics
- Introduction to Evolutionary Computation
- Types of evolutionary algorithms
-
09:15 - 10:00
Lecture: Evolutionary Strategies
10:15 - 12:00
Exercise: GA and ES for function optimization in Python
-
09:15 - 11:00
Lecture: Multi-objective Optimization with Evolutionary Algorithms
11:15 - 12:00
Exercise: NSGA-II for multi-objective optimization in Python
-
09:15 - 12:00
Lecture:
- Foundations of Neural Networks
- Unsupervised Learning
- Supervised Learning
-
09:15 - 12:00
Lecture:
- Supervised Learning (see previous week for slides, check points, and recording)
- Deep, Convolutional networks
- Reinforcement learning
-
09:15 - 12:00
Lecture:
- Evolution of robotic neuro-controllers
- Evolution and learning
-
09:15 - 12:00
Robogen:
- Introduction to the software
- Brain evolution for predefined robotic bodies
-
09:15 - 11:00
Lecture:
- Morphology representations
- Evolution of neural morphologies
- Co-evolution of body and brain morphologies
11:15 - 12:00
Robogen: Body encoding and evolutionary parameters
-
09:15 - 12:00
Robogen: Body-Brain co-evolution
-
09.15 - 10.30
Lecture:
- Competitive and cooperative coevolution
Robogen Graded Project
10:30 - 11:15: BS16011:30 - 12:00: DLLEL 0 28 workshop
-
09:15 - 12:00
Robogen: Introduction to Robogen hardware, handout of kits, access to Discovery Learning Labs (3D printing, soldering, experimentation)
09:15 - 11:00: BS160
11:15 - 12:00: DLLEL 0 28 workshop
-
Ascension day
-
09:15 - 10:00
Lecture: Towards self-reproducing robots
10:15 - 12:00: DLLEL 0 28 workshop
Robogen: Project coaching
-
09:15 - 12:00: BS160
Robogen presentations: Each team gives 8-minute presentation with demo + 2 minutes Q&A
