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
Resilient Collision-tolerant Navigation in Confined Environments
TL;DR: The Resilient Micro Flyer as mentioned in this paper uses elastic flaps around its stiff collision-tolerant frame to ensure compliant collisions, contact sensing and smooth navigation in contact with the environment.
Book ChapterDOI
Extending Deep Neural Network Trail Navigation for Unmanned Aerial Vehicle Operation Within the Forest Canopy
TL;DR: This work presents an optimised deep neural network architecture, capable of state-of-the-art performance across varying resolution aerial UAV imagery, that improves forest trail detection for UAV guidance even when using significantly low resolution images that are representative of low-cost search and rescue capable UAV platforms.
Posted Content
UAV Aided Search and Rescue Operation Using Reinforcement Learning
TL;DR: This paper considers a SAR scenario where the UAV tries to locate a victim trapped in an indoor environment by sensing the RF signals emitted from a smart device owned by the victim, and uses the RSS to define the states and rewards of the RL algorithm.
Journal ArticleDOI
Autonomous quadrotor obstacle avoidance based on dueling double deep recurrent Q-learning with monocular vision
TL;DR: A novel learning-based framework that enables the quadrotor to realize autonomous obstacle avoidance without any prior environment information or labeled datasets for training, and its model can be easily updated while facing new application scenarios.
Journal ArticleDOI
Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation
Srivatsan Krishnan,Behzad Boroujerdian,William Fu,Aleksandra Faust,Vijay Janapa Reddi,Vijay Janapa Reddi +5 more
TL;DR: Air Learning as mentioned in this paper is an open-source simulator and a gym environment for deep reinforcement learning research on resource-constrained aerial robots, which exposes a UAV agent to a diverse set of challenging scenarios.
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.