Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5
0
6
10
Real-time mesh reconstruction can now capture complex underwater topologies and highlight data gaps, transforming how ROVs and AUVs operate in challenging environments.
Achieving state-of-the-art attention prediction with 99.40% lower computational costs, GazeLNN transforms how robots perceive and navigate their environments.
A single control policy can seamlessly adapt to various multirotor configurations, achieving zero-shot transfer to real-world systems in just five minutes of training.
One planner to rule them all: OmniPlanner lets you use the same exploration and inspection strategy across drones, ground robots, and underwater vehicles without significant retuning.
Forget painstakingly retraining: this method slashes multirotor control policy learning time by 73% by intelligently transferring knowledge between different drone configurations.