The majority of learning from demonstration approaches do not address suboptimal
demonstrations or cases when drastic changes in the environment occur after the …

Several approaches have been proposed to assist humans in co-manipulation and
teleoperation tasks given demonstrated trajectories. However, these approaches are not …

A seamless integration of robots into human environments requires robots to learn how to
use existing human tools. Current approaches for learning tool manipulation skills mostly …

One of the key challenges in applying reinforcement learning to complex robotic control
tasks is the need to gather large amounts of experience in order to find an effective policy for …

While teleoperation provides a possibility for a robot to operate at extreme conditions
instead of a human, teleoperating a robot still demands a heavy mental workload from a …

We consider how to most efficiently leverage teleoperator time to collect data for learning
robust image-based value functions and policies for sparse reward robotic tasks. To …

Reinforcement Learning (RL) based methods have became popular for control and motion
planning of robots, recently. Unlike sampling based motion planners, optimal policies …

Simulations are attractive environments for training agents as they provide an abundant
source of data and alleviate certain safety concerns during the training process. But the …

Current methods require robots to be reprogrammed for every new task, consuming many
engineering resources. This work focuses on integrating real and simulated environments …

Reinforcement Learning is a promising tool for learning complex policies even in fast-
moving and object-interactive domains where human teleoperation or hard-coded policies …