27 datasets found

The validation sub-datasets contain 200 images with exactly one visible gate, no visible gate in front, and multiple gates visible.

The perception dataset Dp contains 300k images where a gate is visible and gate-pose annotations are available. The control component uses a dataset Dc of 17k images with UAV...

A wearable assistive device for visually impaired people to navigate safely and quickly in unfamiliar environments, as well as perceive the complicated environment to...

The UNav dataset is an infrastructure-independent vision-based navigation system for people with blindness and low vision.

The dataset used in this paper is a multiagent navigation task environment. Two robots must navigate to their respective targets while avoiding collisions with each other. The...

The SCITOS-G5 robotic navigation benchmark dataset is used to evaluate the proposed approach.

The dataset used in the paper is a replay buffer containing observations from a navigation task.

The dataset used in the paper is a 2-D environment with a starting region S, a destination region D, and an obstacle region ∆. The environment is described by a starting region...

This paper proposes a low-cost six Degree-of-Freedom (6-DOF) navigation system for small aerial robots based on the integration of Global Position System (GPS) receiver with...

The dataset used in this paper is a large-scale demonstration dataset containing 110M and 10M training and validation samples, respectively.

The Room-for-Room (R4R) dataset for instruction conditioned navigation

The Room-to-Room dataset is a photo-realistic dataset for vision-and-language navigation, where agents navigate through indoor environments based on natural language instructions.

The dataset for instruction conditioned navigation using dynamic time warping

The Nordland Railway dataset is a large-scale driving dataset that includes a 728km train journey from Trondheim to Bodø in Nordland, Norway, recorded four times, once per season.

The Room-to-Room (R2R) dataset is a benchmark for vision-and-language navigation tasks. It consists of 7,189 paths sampled from its navigation graphs, each with three...

The dataset used in the paper is a set of environments with different topological properties, including a gridworld, a torus, and a four rooms environment. The agent is tasked...

A dataset for visual homing algorithm, using omnidirectional images and convolutional neural network

A real-world dataset for LiDAR-based end-to-end navigation, consisting of 32km of driving data with 29km for training and 3km for testing.

The dataset used in the paper for vision-and-language navigation tasks.

The dataset used for the magnetic anomaly-based navigation problem, containing a scalar magnetometer measurements and a priori magnetic field map.