VLN-CE RxR (EASI)

VLN-CE RxR Dataset for EASI Vision-and-Language Navigation in Continuous Environments (VLN-CE) Room-across-Room (RxR) benchmark, repackaged for the EASI evaluation framework. Task An agent receives a natural language navigation instruction (in English, Hindi, or Telugu) and must navigate through a Matterport3D indoor environment to reach a goal location. The agent uses discrete actions: STOP, MOVE FORWARD (0.25m), TURN LEFT (30 deg), TURN RIGHT (30 deg), LOOK UP (30 deg)… See the full description on the dataset page: easi.

Source: Hugging Face Hub (oscarqjh/VLN-CE-RxR_easi). Metadata imported from the dataset’s Hub tags.