Proceedings ArticleDOI
Learning to fly by crashing
Dhiraj Gandhi,Lerrel Pinto,Abhinav Gupta +2 more
- pp 3948-3955
Reads0
Chats0
TLDR
This paper builds a drone whose sole purpose is to crash into objects: it samples naive trajectories and crashes into random objects to create one of the biggest UAV crash dataset.Abstract:
How do you learn to navigate an Unmanned Aerial Vehicle (UAV) and avoid obstacles? One approach is to use a small dataset collected by human experts: however, high capacity learning algorithms tend to overfit when trained with little data. An alternative is to use simulation. But the gap between simulation and real world remains large especially for perception problems. The reason most research avoids using large-scale real data is the fear of crashes! In this paper, we propose to bite the bullet and collect a dataset of crashes itself! We build a drone whose sole purpose is to crash into objects: it samples naive trajectories and crashes into random objects. We crash our drone 11,500 times to create one of the biggest UAV crash dataset. This dataset captures the different ways in which a UAV can crash. We use all this negative flying data in conjunction with positive data sampled from the same trajectories to learn a simple yet powerful policy for UAV navigation. We show that this simple self-supervised model is quite effective in navigating the UAV even in extremely cluttered environments with dynamic obstacles including humans. For supplementary video see:read more
Citations
More filters
Proceedings ArticleDOI
RSS-Based Q-Learning for Indoor UAV Navigation
TL;DR: In this article, the authors focus on the potential use of unmanned aerial vehicles (UAVs) for search and rescue (SAR) missions in GPS-denied indoor environments and consider the problem of navigating a UAV to a wireless signal source, e.g., a smartphone or watch owned by a victim.
Journal ArticleDOI
Flying Free: A Research Overview of Deep Learning in Drone Navigation Autonomy
TL;DR: A taxonomy of drone navigation autonomy is established by mapping the definitions of vehicular autonomy levels to specific drone tasks in order to create a clear definition of autonomy when applied to drones.
Journal ArticleDOI
Barriers to adoption of RPAs on construction projects: a task-technology fit perspective
Hamed Golizadeh,M. Reza Hosseini,David J. Edwards,Sepehr Abrishami,Nasrin Taghavi,Saeed Banihashemi +5 more
TL;DR: In this paper, a review of the literature on the use of remotely piloted aircrafts (RPAs) for construction activities is presented, where the authors identify, collated and categorized five thematic groups, namely technical difficulties, restrictive regulatory environment, site-related problems, weather and organizational barriers.
Posted Content
VisualEchoes: Spatial Image Representation Learning through Echolocation
TL;DR: This work captures echo responses in photo-realistic 3D indoor scene environments and proposes a novel interaction-based representation learning framework that learns useful visual features via echolocation that is comparable or even better than heavily supervised pre-training.
Journal ArticleDOI
A UAV-assisted CH Election Framework for Secure Data Collection in Wireless Sensor Networks
TL;DR: A UAV-assisted CH election framework which collects residual energy of nodes, and employs them for electing new CHs and excluding the lowest energy nodes from CH candidates, which provides better security and performance than the generalCH election framework with a short CH election period.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Proceedings ArticleDOI
Parallel Tracking and Mapping for Small AR Workspaces
Georg Klein,David W. Murray +1 more
TL;DR: A system specifically designed to track a hand-held camera in a small AR workspace, processed in parallel threads on a dual-core computer, that produces detailed maps with thousands of landmarks which can be tracked at frame-rate with accuracy and robustness rivalling that of state-of-the-art model-based systems.