On the other hand, while physical interaction with these objects has been done with ground manipulators, there have not been any studies on physical interaction and manipulation of the deformable linear object with aerial robots.
On the other hand, algorithms that entirely separate the spatial representation of the deformable object from the routing and manipulation, often using a representation approach independent of planning, result in slow planning in high dimensional space.
The canonical object representation is learned solely in simulation and then used to parse a category-level, task trajectory from a single demonstration video.
To the best of our knowledge, the topic of detection methods that can extract those initial conditions in non-trivial situations has hardly been addressed.
In this work, we extend hindsight relabelling mechanisms to guide exploration along task-specific distributions implied by a small set of successful demonstrations.
no code implementations • 28 Oct 2021 • Nicholas Roy, Ingmar Posner, Tim Barfoot, Philippe Beaudoin, Yoshua Bengio, Jeannette Bohg, Oliver Brock, Isabelle Depatie, Dieter Fox, Dan Koditschek, Tomas Lozano-Perez, Vikash Mansinghka, Christopher Pal, Blake Richards, Dorsa Sadigh, Stefan Schaal, Gaurav Sukhatme, Denis Therien, Marc Toussaint, Michiel Van de Panne
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains.
This work proposes a framework to learn task-relevant grasping for industrial objects without the need of time-consuming real-world data collection or manual annotation.
Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications.
In this paper we define criteria for industry-oriented DRL, and perform a thorough comparison according to these criteria of one family of learning approaches, DRL from demonstration, against a professional industrial integrator on the recently established NIST assembly benchmark.
In recent years, many learning based approaches have been studied to realize robotic manipulation and assembly tasks, often including vision and force/tactile feedback.
Dynamic Movement Primitives (DMP) are a popular way of extracting such policies through behaviour cloning (BC) but can struggle in the context of insertion.
In December 2014, a two-day workshop supported by the Computing Community Consortium (CCC) and the National Science Foundation's Computer and Information Science and Engineering Directorate (NSF CISE) was convened in Washington, DC, with the goal of bringing together computer scientists and brain researchers to explore these new opportunities and connections, and develop a new, modern dialogue between the two research communities.
We complete unseen tasks by choosing new sequences of skill latents to control the robot using MPC, where our MPC model is composed of the pre-trained skill policy executed in the simulation environment, run in parallel with the real robot.
In particular, we first use simulation to jointly learn a policy for a set of low-level skills, and a "skill embedding" parameterization which can be used to compose them.
State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification.
In this work, we investigate the advantages and limitations of neural network based learning approaches for predicting the effects of actions based on sensory input and show how analytical and learned models can be combined to leverage the best of both worlds.
The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks.
Imitation learning has traditionally been applied to learn a single task from demonstrations thereof.
While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.
Ranked #3 on Video Alignment on UPenn Action
In practice, the parameters of control policies are often tuned manually.
We extend GPS in the following ways: (1) we propose the use of a model-free local optimizer based on path integral stochastic optimal control (PI2), which enables us to learn local policies for tasks with highly discontinuous contact dynamics; and (2) we enable GPS to train on a new set of task instances in every iteration by using on-policy sampling: this increases the diversity of the instances that the policy is trained on, and is crucial for achieving good generalization.
This model is non-linear and non-convex; however, we find a relaxation of the problem that allows us to formulate it as a single convex quadratically-constrained quadratic program (QCQP) that can be very efficiently optimized.
With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data.
Recent approaches in robotics follow the insight that perception is facilitated by interaction with the environment.
To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand.
The contribution of this paper is to show that any Gaussian filter can be made compatible with fat-tailed sensor models by applying one simple change: Instead of filtering with the physical measurement, we propose to filter with a pseudo measurement obtained by applying a feature function to the physical measurement.
In this paper, we derive a probabilistic registration algorithm for object modeling and tracking.
Locally weighted regression (LWR) was created as a nonparametric method that can approximate a wide range of functions, is computationally efficient, and can learn continually from very large amounts of incrementally collected data.
Locally weighted regression was created as a nonparametric learning method that is computationally efficient, can learn from very large amounts of data and add data incrementally.
In this paper, we focus on nonparametric regression and introduce a Bayesian formulation that, with the help of variational approximations, results in an EM-like algorithm for simultaneous estimation of regression and kernel parameters.