10 papers with code • 1 benchmarks • 1 datasets
(Satellite -> Drone) Given one satellite-view image, the drone intends to find the most relevant place (drone-view images) that it has passed by. According to its flight history, the drone could be navigated back to the target place.
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
We analyze the rich latent spaces learned with our proposed representations, and show that the use of our cross-modal architecture significantly improves control policy performance as compared to end-to-end learning or purely unsupervised feature extractors.
his paper presents a simple approach for drone navigation to follow a predetermined path using visual input only without reliance on a Global Positioning System (GPS).
The STS model can run at 35 FPS on a high-end desktop, but its accuracy is significantly worse than that of offline state-of-the-art methods.
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch.
However it still has some limitations, e. g., it can only extract part of the information in the neighborhood and some scale reduction operations will make some fine-grained information lost.
Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning
Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones.
Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.
While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs.