Tag
This paper proposes a Latent World Model (LWM) for robot navigation that predicts action-conditioned latent feature compatibility, enabling policy learning from unlabeled video data and reinforcement learning without additional environment interaction, outperforming existing methods.
This paper proposes a proxemics-based reward formulation for deep reinforcement learning social navigation, modeling human personal space as Gaussian-mixture fields to improve social compliance while maintaining navigation efficiency.
This paper introduces a continuous metric field framework trained by a single causal contrastive loss that unifies geometric structure discovery from robot navigation to black hole emergence, demonstrating zero-shot generalization across dimensions.
UniNav is a unified world-action diffusion model for image-goal visual navigation that jointly predicts future visual observations and waypoint trajectories in a single diffusion process, achieving strong benchmark results with efficient inference.
FLYNN is a recurrent neural network derived from the fruit fly brain connectome for vision-based robot navigation. It achieves comparable performance to handcrafted networks while showing superior robustness to out-of-distribution data and sensory loss.
PlatonicNav introduces a training-free framework for embodied navigation that uses vision-only semantic maps and blind matching to ground language goals, achieving generalization across tasks and embodiments without explicit cross-modal training.