Maren Bennewitz

MS-MEM achieves higher mapping accuracy while minimizing scene disturbances, showcasing the power of integrating multiple manipulation skills in robotic perception.

By effectively predicting unobserved plant structures, SG-AMP enhances active perception and motion planning, achieving notable improvements in semantic accuracy and depth estimation.

Real-world datasets reveal that tracking tomato ripeness can significantly enhance agricultural automation and phenotyping techniques.

Uncertainty can be harnessed to enhance the reliability of depth-only 3D semantic segmentation without compromising privacy.

3D diffusion models can be harnessed to generate object priors for one-shot view planning, enabling robots to efficiently reconstruct objects by focusing on complex regions.