Search papers, labs, and topics across Lattice.
5
0
5
25
Communicative clarity in robots peaks at two degrees of freedom, challenging the notion that more complex motion always enhances expressiveness.
Optimizing individual finger designs can lead to substantial performance gains in robotic hand tasks, transforming how we approach dexterous manipulation.
Achieve a 50% boost in real-world control of tendon-driven robots by training RL policies in simulation with a learned tendon force model, bridging the sim-to-real gap.
Forget computationally expensive fluid dynamics: this work shows that a simple, stateless model, carefully calibrated to real-world data, can create surprisingly effective digital twins for soft underwater robots.
Forget hand-tuning your robot simulator: this system uses paired real-world videos and language models to automatically diagnose and fix physics mismatches with interpretable rationales.
