Showing cs.AIShow all
2 papers · 1 filter
cs.AI2024
HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation
Naoki Yokoyama, Ram Ramrakhya, Abhishek Das +2
We present the Habitat-Matterport 3D Open Vocabulary Object Goal Navigation dataset (HM3D-OVON), a large-scale benchmark that broadens the scope and semantic range of prior Object…
cs.AI2024
GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
Mukul Khanna, Ram Ramrakhya, Gunjan Chhablani +7
The Embodied AI community has made significant strides in visual navigation tasks, exploring targets from 3D coordinates, objects, language descriptions, and images. However, these…