Search papers, labs, and topics across Lattice.
4
0
4
PartialBiGrasp enables dual-arm robots to grasp complex objects with only partial geometric information, achieving stability where previous methods fail.
SILICA achieves a nearly 20% improvement in depth estimation accuracy for transparent surfaces without requiring real-world glass depth annotations.
Modular grasp synthesis pipelines that decompose grasping into pose/shape estimation followed by antipodal grasp sampling can surprisingly outperform end-to-end methods, even leveraging vision-language models for language-conditioned grasping.
By blending LLM-based prediction with probabilistic planning, robots can now proactively anticipate and mitigate human-related task failures, leading to more robust human-robot collaboration.
