Showing 2024Show all
3 papers · 1 filter
cs.RO2024
Agent-Based Emulation for Deploying Robot Swarm Behaviors
Ricardo Vega, Kevin Zhu, Connor Mattson +2
Despite significant research, robotic swarms have yet to be useful in solving real-world problems, largely due to the difficulty of creating and controlling swarming behaviors in m…
cs.NE2024
Spiking Neural Networks as a Controller for Emergent Swarm Agents
Kevin Zhu, Connor Mattson, Shay Snyder +4
Drones which can swarm and loiter in a certain area cost hundreds of dollars, but mosquitos can do the same and are essentially worthless. To control swarms of low-cost robots, res…
cs.RO2024
Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations
Connor Mattson, Anurag Aribandi, Daniel S. Brown
We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then tran…