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
Posted Content
Learning Long-Range Perception Using Self-Supervision from Short-Range Sensors and Odometry
TL;DR: In this paper, a general self-supervised approach is proposed to predict the future outputs of a short-range sensor (such as a proximity sensor) given the current outputs of long-range sensors such as a camera.
Proceedings ArticleDOI
Indoor Multi-Sensory Self-Supervised Autonomous Mobile Robotic Navigation
Juhong Xu,Hanqing Guo,Shaoen Wu +2 more
TL;DR: This work proposes a novel solution to eliminate the need of human manual labeling after the initial data collection in the task of imitating to navigate in indoor environments with an imperfect policy based on multi-sensor fusion and a recording policy that only records the data giving the most knowledge to the navigation policy.
Posted Content
Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach.
TL;DR: In this article, the authors presented the first attempt to categorize faults occurring in deep reinforcement learning (DRL) programs and developed DRLinter, a model-based fault detection approach that leverages static analysis and graph transformations.
Posted Content
Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces.
TL;DR: This work introduces an approach to model surface properties governing bounces in everyday scenes and shows that the proposed model out-performs baselines, including trajectory fitting with Newtonian physics, in predicting post-bounce trajectories and inferring physical properties of a scene.
Posted Content
Learning visual policies for building 3D shape categories
TL;DR: This work proposes a disassembly procedure and learns a state policy that discovers new object instances and their assembly plans in state space and demonstrates the reactive ability of the method to re-assemble objects using additional primitives and the robust performance of the policy for unseen primitives resembling building blocks used during training.
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.