KAMPUS26 is a private "study in public" and research project that aims to learn about and share knowledge and insights about recent advances in decentralized robotics and swarm intelligence. The project is not affiliated with any organization or institution, but is inspired by the Distributed Autonomous Robotic Systems (DARS) Symposium series, which is a biennial forum for scientific exchange and technical communication on the latest advances in distributed robotics.
This self-study plan has two tracks: One will roughly follow the synopsis of papers presented at the 2023 DARS symposium and will involve reading and summarizing papers, writing blog posts and creating other materials that may be useful to the community, while the other will be more focused on implementing genetic algorithms in Elixir and using them to solve real-world problems.
The project will be conducted in the open, and all materials will be shared on GitHub.
- Writing Your First Genetic Algorithm
- Breaking Down Genetic Algorithms
- Encoding Problems and Solutions
- Evaluating Solutions and Populations
- Selecting the Best
- Generating new solutions
- Preventing Premature Convergence
- Replacing and Transitioning
- Tracking Genetic Algorithms
- Visualizing the Results
- Optimizing Your Algorithm
- Writing Tests and Code Quality
- Moving Forward
- Generating Goal Configurations for Scalable Shape Formation in Robotic Swarms
- Leading a Swarm with Signals
- Byzantine Fault Tolerant Consensus for Lifelong and online Multi-Robot Pickup and Delivery
- Decentralized Multi-Robot Path Planning in Dynamic 3D Environments
- Optimized Direction Assignment in Road Maps for Multi-AVG Systems based on Transportation Flows
- Datom: A Deformable Modular Robot for Building Self-reconfigurable Programmable Matter
- The Impact of Network Connectivity on Collective Learning
- On the Communication Requirements of Decentralized Connectivity Control: A Field Experiment
- Behavioral Simulations of Lattice Modular Robots with VisibleSim
- Evolving Robust Supervisors in Uncertain Complex Environments
- Distributed Cooperative Localization with Efficient Pairwise Range Measurements
- Robust Localization for Multi-Robot Formations: An Experimental Evaluation of an Extended GM-PHD Filter
- Opportunistic Multi-Robot Environmental Sampling via Decentralized Markov Decision Processes
- A PHD Filter based Localization System for Robotic Swarms
- Online Onboard Evolution of Manipulation Behaviors for a Multi-robot System
- Multi-Agent Reinforcement Learning and Individuality Analysis for Cooperative Transportation with Object Removal
- Battery Variability Management for Swarms
- Spectral-based Distributed Ergodic Coverage for Heterogeneous Multi-Agent Search
- Multi-Agent Deception in Attack-Defense Stochastic Games
- Traceable Planning for Coordinated Story Capture: Sequential Stochastic Decoupling
- Errors in Collective Robotic Construction
- Optimal Multi-Robot Perimeter Defense using Flow Networks
- Classification-Aware Path Planning of Network of Robots
- Monitoring and Mapping of Crop Fields with UAV Swarms based on Information Gain
- A Discrete Model of Collective Marching on Rings
- Map Learning via Adaptive Region-based Sampling in Multi-Robot Systems
- Collective Transport via Sequential Caging
- ReactiveBuild: Environment-Adaptive Self-Assembly of Amorphous Structures
- Processes for a Colony Solving the Best-of-N Problem using a Bipartite Graph Representation
- Decentralized Navigation in 3D Space of a Robotic Swarm with Heterogeneous Abilities
- Using Reinforcement Learning to Herd a Robotic Swarm to a Target Distribution
- Preservation of Giant Component Size After Robot Failure for Robustness of Multi-Robot Networks
- Swarm Localization Through Cooperative Landmark Identification