dist_to_end_reduction: 4.46spl: 0.23
Papers with Code · CC BY-SA 4.0
Visual Navigation
Visual Navigation is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.
<span class="description-source">Source: Vision-based Navigation Using Deep Reinforcement Learning </span>
논문
dist_to_end_reduction: 7.90spl: 0.09
dist_to_end_reduction: 2.35spl: 0.16
dist_to_end_reduction: 6.13spl: 0.07
spl: 0.6383
spl: 0.60
dist_to_end_reduction: 3.91spl: 0.17
spl: 0.59
SPL (All): 16.15Success Rate (All): 40.86SPL (L≥5): 13.91Success Rate (L≥5): 28.7
spl: 0.61
Medium Human-Normalized Score: 72.8%
SPL (All): 17.27Success Rate (All): 48.7SPL (L≥5): 13.63Success Rate (L≥5): 30.9
spl: 0.58
spl: 28.72