Exploiting Heterogeneity
We are developing decentralized control algorithms that can guarantee robust connectivity in a group of heterogeneous agents, e.g., quadrotors and OctoRoACHES, that are used for searching an area of interest, detecting and tracking targets, or surveilling complex environments. Also, we study and evaluate experimentally the implementation of an optical wireless (OW) communication link between aerial and ground micro-sized robotic agents for compatibility with such operations. Click here to learn more.



F1/10 Racing
The UNM MARHES Lab racing team, LoboRacers won 2nd place in the first ever F1/10 International Autonomous Racing Competition at Carnegie Mellon University on October 1-2, 2016. The F1/10 Competition involves assembling, programming, and racing an autonomous car of one-tenth scale of an actual automobile with the ultimate goal of developing advanced algorithms that could be applied to self-driving cars in the future. Click here to learn more.



Aerial Transportation
We are interested in the challenging problem of using quadrotors to transport and manipulate loads safely and efficiently. Flying with a cable-suspended load is a hazardous task since the payload significantly changes the flight characteristics of the aerial vehicle. Therefore, the stability of the vehicle-load system must be preserved for safe operation. It is essential that the flying robot has the ability to adapt to changes in the system dynamics and reduce undesired effects, e.g. the swing of the load, during assigned maneuvers. Click here to learn more.



Learning and Control
Reinforcement Learning (RL) has grown as an effective approach for multi-robot cooperative control. We study and apply this method, so a robotic team can perform motions to complete a task by learning through experimentation. Robots received information about their world, make a near-optimal decision applying RL with the goal in mind, and perform the option in order to maximize a reward defined based on a final global goal. Click here to learn more.


Comments are closed