Search papers, labs, and topics across Lattice.
8
0
5
ELMP slashes adaptation costs for motion planning by two orders of magnitude while boosting success rates in unseen environments to nearly 90%.
Optimization-guided diffusion not only ensures feasibility in robot control tasks but also enhances task success rates by up to 23 percentage points without retraining the model.
Real-world robots can now leverage photo-realistic digital twins constructed directly from RGB-D videos, eliminating the need for manual modeling.
Zero-shot sim-to-real transfer is achieved with a 16.7% reduction in force prediction error by aligning diverse tactile modalities in a shared latent space.
GAM revolutionizes robot policy learning by seamlessly integrating 3D geometric reasoning, outperforming traditional models in accuracy and efficiency.
Achieving mean absolute errors as low as 0.14 N in dense force estimation could revolutionize tactile feedback in robotic systems.
Forget tedious robot training: VR-DAgger lets you teleoperate robots in VR, slashing data needs and boosting performance by focusing expert corrections where the robot is most uncertain.
Evolutionary optimization in high-fidelity simulators unlocks a 6x boost in stable, diverse dexterous grasps compared to traditional analytical methods.
