Two less addressed issues of deep reinforcement learning are (1) lack of generalization
capability to new goals, and (2) data inefficiency, ie, the model requires several (and often …

Abstract We introduce Interactive Question Answering (IQA), the task of answering questions
that require an autonomous agent to interact with a dynamic visual environment. IQA …

Nowadays, the field of mobile robotics is experiencing a quick evolution, and a variety of
autonomous vehicles is available to solve different tasks. The advances in computer vision …

Many robotic applications require the agent to perform long-horizon tasks in partially
observable environments. In such applications, decision making at any step can depend on …

In this paper, we present incremental smoothing and map** (iSAM), which is a novel
approach to the simultaneous localization and map** problem that is based on fast …

Mobile robot vision-based navigation has been the source of countless research
contributions, from the domains of both vision and control. Vision is becoming more and …

In this article, we develop a navigation strategy based on deep reinforcement learning (DRL)
for mobile robots. Because of the large difference between simulation and reality, most of the …

We propose a learning-based navigation system for reaching visually indicated goals and
demonstrate this system on a real mobile robot platform. Learning provides an appealing …

We present experimental results demonstrating monocular SLAM as a human carries a
camera over long walked trajectories in outdoor areas with people and other clutter, even in …

Safety is a critical component of autonomous systems and remains a challenge for learning-
based policies to be utilized in the real world. In particular, policies learned using …