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.
Source: Vision-based Navigation Using Deep Reinforcement Learning
Papers
Showing 1–10 of 316 papers
All datasetsCooperative Vision-and-Dialogue NavigationR2RSOON TestAI2-THORDmlab-30Help, Anna! (HANNA)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | NaviLLM | dist_to_end_reduction | 7.9 | — | Unverified |
| 2 | VLN-PETL | dist_to_end_reduction | 6.13 | — | Unverified |
| 3 | early to bed | dist_to_end_reduction | 6.03 | — | Unverified |
| 4 | HAMT | dist_to_end_reduction | 5.58 | — | Unverified |
| 5 | s-agent (NDH-Full) | dist_to_end_reduction | 5.27 | — | Unverified |
| 6 | BabyWalk (r2r-pretrain) | dist_to_end_reduction | 4.46 | — | Unverified |
| 7 | Environment-agnostic Multitask Learning | dist_to_end_reduction | 3.91 | — | Unverified |
| 8 | BabyWalk | dist_to_end_reduction | 3.65 | — | Unverified |
| 9 | Test2-NDH | dist_to_end_reduction | 3.44 | — | Unverified |
| 10 | SCoA | dist_to_end_reduction | 3.37 | — | Unverified |