Selected Publications
DDA: Deep Drone Acrobatics
We propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation. We train the policy entirely in simulation by leveraging demonstrations from an optimal controller that has access to privileged information. We use appropriate abstractions of the visual input to enable transfer to a real quadrotor. We show that the resulting policy can be directly deployed in the physical world without any fine-tuning on real data. Our methodology has several favorable properties: it does not require a human expert to provide demonstrations, it cannot harm the physical system during training, and it can be used to learn maneuvers that are challenging even for the best human pilots. Our approach enables a physical quadrotor to fly maneuvers such as the Power Loop, the Barrel Roll, and the Matty Flip, during which it incurs accelerations of up to 3g.
RSS’20
SGAS: Sequential Greedy Architecture Search
We introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost.
CVPR’20
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
We present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks. To do this, we re-frame the adversarial attack problem as learning a distribution of parameters that always fools the agent. In the semantic case, our proposed adversary (denoted as BBGAN) is trained to sample parameters that describe the environment with which the black-box agent interacts, such that the agent performs its dedicated task poorly in this environment. We apply BBGAN on three different tasks, primarily targeting aspects of autonomous navigation: object detection, self-driving, and autonomous UAV racing. On these tasks, BBGAN can generate failure cases that consistently fool a trained agent.
Poster at AAAI’20
DeepGCNs: Making GCNs Go as Deep as CNNs
GCNs show promising results, but they are limited to very shallow models due to the vanishing gradient problem. As a result most state-of-the-art GCN algorithms are no deeper than 3 or 4 layers. In this work, we present new ways to successfully train very deep GCNs. We borrow concepts from CNNs, mainly residual/dense connections and dilated convolutions, and adapt them to GCN architectures. Through extensive experiments, we show the positive effect of these deep GCN frameworks. Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3.7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation.
Oral at ICCV’19
OIL: Observational Imitation Learning
We propose Observational Imitation Learning (OIL), a novel imitation learning variant that supports online training and automatic selection of optimal behavior by observing multiple imperfect teachers. We apply our proposed methodology to the challenging problems of autonomous driving and UAV racing. For both tasks, we utilize the Sim4CV simulator that enables the generation of large amounts of synthetic training data and also allows for online learning and evaluation. We train a perception network to predict waypoints from raw image data and use OIL to train another network to predict controls from these waypoints. Extensive experiments demonstrate that our trained network outperforms its teachers, conventional imitation learning (IL) and reinforcement learning (RL) baselines and even humans in simulation.
RSS’19
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing
In this paper, we propose learning an optimized controller using a DNN that fuses multiple controllers. The network learns a robust controller with online trajectory filtering, which suppresses noisy trajectories and imperfections of individual controllers. The result is a network that is able to learn a good fusion of filtered trajectories from different controllers leading to significant improvements in overall performance. We compare our trained network to controllers it has learned from, end-to-end baselines and human pilots in a realistic simulation; our network beats all baselines in extensive experiments and approaches the performance of a professional human pilot.
CVPRW’19 - UAVision’19
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
We present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved.
ECCV’18
Driving Policy Transfer via Modularity and Abstraction
We present an approach for transferring driving policies from simulation to reality via modularity and abstraction. Our approach is inspired by classic driving systems and aims to combine the benefits of modular architectures and end-to-end deep learning approaches. The key idea is to encapsulate the driving policy such that it is not directly exposed to raw perceptual input or low-level vehicle dynamics. We evaluate the presented approach in simulated urban environments and in the real world. In particular, we transfer a driving policy trained in simulation to a 1/5-scale robotic truck that is deployed in a variety of conditions, with no finetuning, on two continents.
CoRL’18
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications
We present a photo-realistic training and evaluation simulator [Sim4CV](https://sim4cv.org/) with extensive applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator integrates full featured physics based cars, unmanned aerial vehicles (UAVs), and animated human actors in diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning. The simulator fully integrates both several state-of-the-art tracking algorithms with a benchmark evaluation tool and a deep neural network (DNN) architecture for training vehicles to drive autonomously. It generates synthetic photo-realistic datasets with automatic ground truth annotations to easily extend existing real-world datasets and provides extensive synthetic data variety through its ability to reconfigure synthetic worlds on the fly using an automatic world generation tool.
IJCV’18
End-to-end Driving via Conditional Imitation Learning
A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands. Experimental results demonstrate that the presented approach significantly outperforms a number of baselines.
ICRA’18
Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when sufficient data augmentation is used) outperforms state-of-the-art methods and flies more consistently than many human pilots.
ECCVW’18 - UAVision’18
Context-Aware Correlation Filter Tracking
In this paper, we present a framework that allows the explicit incorporation of global context within CF trackers. We reformulate the original optimization problem and provide a closed form solution for single and multi-dimensional features in the primal and dual domain. We demonstrate with extensive experiments that this framework can significantly improve the performance of many CF trackers with only a modest impact on their frame rate.
Oral at CVPR’17
A Benchmark and Simulator for UAV Tracking
In order to evaluate object trackers for aerial tracking applications, we have generated 123 new video sequences from a UAV and annotated them with upright bounding boxes and attributes relevant for tracking. With more than 110,000 frames this is currently the largest data set for aerial tracking by a long shot and the second largest data set for generic tracking. In addition, we have developed a photo-realistic simulator within the UE4 framework that can be used for numerous vision tasks. As an example, we have integrated several state-of-the-art object trackers to control an UAV inside the simulator based on live feedback. In addition our simulator can be used to generate large amounts of realistic vision data.
Poster at ECCV’16
Persistent Aerial Tracking System for UAVs
We have developed a persistent, robust and autonomous object tracking system for unmanned aerial vehicles (UAVs). Our computer vision and control strategy integrates multiple UAVs with a stabilized RGB camera and can be applied to a diverse set of moving objects (e.g. humans, animals, cars, boats, etc.). A novel strategy is employed to successfully track objects over a long period, by ’handing over the camera’ from one UAV to another. The popular object tracker Struck was optimized for both speed and performance and integrated into the proposed system.
Interactive Presentation at IROS’16