Search papers, labs, and topics across Lattice.
Robert Bosch GmbH, Stuttgart, Germany Robot Learning Lab, University of Freiburg, Freiburg, Germany 22email:
7
0
5
Saliency-driven masking in video self-supervised learning can boost performance in autonomous driving tasks by preserving critical context that traditional random masking overlooks.
Action-derived visual attention can boost robot task success rates by over 28% without relying on external labels.
Caregivers are optimistic about care robots for logistical tasks but wary of their role in emotionally sensitive interactions, revealing a complex landscape of acceptance and ethical concerns.
Location-informed ReID can cut expert review needs by nearly 70% while boosting identification accuracy in challenging wildlife surveys.
Achieving state-of-the-art 4D panoptic occupancy tracking, this method maintains temporal coherence in scene representations without the computational burden of recomputing volumetric data at each timestep.
Hardware selection can make or break SLAM performance in quadrupedal robots, with stereo setups and global shutter cameras proving crucial for resilience in dynamic environments.
Robots can now learn to navigate diverse terrains continuously and without human labels, adapting to new environments and even transferring skills across different robot types.
