4 datasets found

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

The RoboTHOR dataset is a simulation environment for embodied AI research, containing 15 validation environments with 12 different goal object categories.

A novel reward function for reinforcement learning and a Soft Actor-Critic algorithm to train a DRL policy in the context of local navigation for autonomous mobile robots in...

The dataset used in the paper is the AI2-THOR dataset, which is a 3D indoor environment dataset. The agent must navigate from a random starting position to a pre-specified...