Search Results for author:
Found 19 papers, 3 papers with code
DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
We present DemoStart, a novel auto-curriculum reinforcement learning method capable of learning complex manipulation behaviors on an arm equipped with a three-fingered robotic hand, from only a sparse reward and a handful of demonstrations in simulation.
simPLE: a visuotactile method learned in simulation to precisely pick, localize, regrasp, and place objects
We propose simPLE (simulation to Pick Localize and PLacE) as a solution to precise pick-and-place.
RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task.
FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback
FingerSLAM is constructed with two constituent pose estimators: a multi-pass refined tactile-based pose estimator that captures movements from detailed local textures, and a single-pass vision-based pose estimator that predicts from a global view of the object.
Tac2Pose: Tactile Object Pose Estimation from the First Touch
This results in a perception model that localizes objects from the first real tactile observation.
Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering
In this paper, we present an approach to tactile pose estimation from the first touch for known objects.
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations.
Experience-Embedded Visual Foresight
In this paper, we tackle the generalization problem via fast adaptation, where we train a prediction model to quickly adapt to the observed visual dynamics of a novel object.
Accurate Vision-based Manipulation through Contact Reasoning
Planning contact interactions is one of the core challenges of many robotic tasks.
Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
Such models, however, are approximate, which limits their applicability.
Tactile Mapping and Localization from High-Resolution Tactile Imprints
This work studies the problem of shape reconstruction and object localization using a vision-based tactile sensor, GelSlim.
Graph Element Networks: adaptive, structured computation and memory
We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure.
Combining Physical Simulators and Object-Based Networks for Control
Physics engines play an important role in robot planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically.
Modular meta-learning in abstract graph networks for combinatorial generalization
Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways.
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
An efficient, generalizable physical simulator with universal uncertainty estimates has wide applications in robot state estimation, planning, and control.
A Data-Efficient Approach to Precise and Controlled Pushing
Decades of research in control theory have shown that simple controllers, when provided with timely feedback, can control complex systems.
Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Since product images are readily available for a wide range of objects (e. g., from the web), the system works out-of-the-box for novel objects without requiring any additional training data.
GP-SUM. Gaussian Processes Filtering of non-Gaussian Beliefs
On the other hand, it achieves effective sampling and accurate probabilistic propagation by relying on the GP form of the system, and the sum-of-Gaussian form of the belief.
A probabilistic data-driven model for planar pushing
This paper presents a data-driven approach to model planar pushing interaction to predict both the most likely outcome of a push and its expected variability.
