Search papers, labs, and topics across Lattice.
University of Engineering and Technology, Vietnam National University
6
0
6
UAVs can achieve up to 94% exploration coverage by focusing on semantically rich areas, revolutionizing indoor mapping efficiency.
Spatio-temporal reasoning boosts continuous semantic mapping accuracy by over 12%, revolutionizing how robots perceive dynamic environments.
Achieving 86.79% action classification accuracy, this framework outperforms existing methods by over 80% in generating precise robotic commands from video demonstrations.
Achieving high synchronization accuracy in humanoid robot gestures requires a delicate balance of semantic understanding and kinematic feasibility, and WaveSync delivers just that.
Hybrid TD3 stabilizes reinforcement learning in hybrid action spaces by taming overestimation bias with a theoretically grounded weighted clipped Q-learning target.
Robots can now learn manipulation skills from unstructured videos with significantly improved accuracy and generalization by decoupling video understanding from policy learning.
