Related papers: Zero-Shot Reinforcement Learning with Deep Attenti…

We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…

The sample efficiency challenge in Deep Reinforcement Learning (DRL) compromises its industrial adoption due to the high cost and time demands of real-world training. Virtual environments offer a cost-effective alternative for training DRL…

Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

In autonomous and mobile robotics, one of the main challenges is the robust on-the-fly perception of the environment, which is often unknown and dynamic, like in autonomous drone racing. In this work, we propose a novel deep neural…

Simulation based learning often provides a cost-efficient recourse to reinforcement learning applications in robotics. However, simulators are generally incapable of accurately replicating real-world dynamics, and thus bridging the sim2real…

Deep convolutional neural networks (CNNs) have been shown to perform extremely well at a variety of tasks including subtasks of autonomous driving such as image segmentation and object classification. However, networks designed for these…

Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments…

Mobile network that millions of people use every day is one of the most complex systems in the world. Optimization of mobile network to meet exploding customer demand and reduce capital/operation expenditures poses great challenges. Despite…

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…

Dynamically changing environments, unreliable state estimation, and operation under severe resource constraints are fundamental challenges that limit the deployment of small autonomous drones. We address these challenges in the context of…

Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…

Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional…

The generalization of the end-to-end deep reinforcement learning (DRL) for object-goal visual navigation is a long-standing challenge since object classes and placements vary in new test environments. Learning domain-independent visual…

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…

Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain…

Through deep learning and computer vision techniques, driving manoeuvres can be predicted accurately a few seconds in advance. Even though adapting a learned model to new drivers and different vehicles is key for robust driver-assistance…

Training deep neural network policies end-to-end for real-world applications so far requires big demonstration datasets in the real world or big sets consisting of a large variety of realistic and closely related 3D CAD models. These real…

People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and more biased toward the…

Deep networks devour millions of precisely annotated images to build their complex and powerful representations. Unfortunately, tasks like autonomous driving have virtually no real-world training data. Repeatedly crashing a car into a tree…