Most dynamics functions are not well-aligned to task requirements.
Contr...
Roboticists frequently turn to Imitation learning (IL) for data efficien...
Sampling-based model predictive control (MPC) is a promising tool for
fe...
We consider the problem of learning motion policies for acceleration-bas...
Robotic tasks often require generation of motions that satisfy multiple
...
This paper describes the pragmatic design and construction of geometric
...
Generating robot motion for multiple tasks in dynamic environments is
ch...
Algorithmic solutions for the motion planning problem have been investig...
This work addresses the problem of robot interaction in complex environm...
Robotic tasks often require motions with complex geometric structures. W...
Traditional robotic approaches rely on an accurate model of the environm...
Effective human-robot collaboration requires informed anticipation. The ...
Teleoperation offers the possibility of imparting robotic systems with
s...
RMPflow is a recently proposed policy-fusion framework based on differen...
Visual topological navigation has been revitalized recently thanks to th...
It is difficult to create robust, reusable, and reactive behaviors for r...
End-to-end learning for autonomous navigation has received substantial
a...
To perform complex tasks, robots must be able to interact with and manip...
We develop a novel policy synthesis algorithm, RMPflow, based on
geometr...
In order to achieve a dexterous robotic manipulation, we need to equip o...
We present a predictor-corrector framework, called PicCoLO, that can
tra...
Current methods for estimating force from tactile sensor signals are eit...
We consider the problem of transferring policies to the real world by
tr...
Modern robotics is gravitating toward increasingly collaborative human r...
We present a simple, yet effective, approach to Semi-Supervised Learning...