Found 22 results.


active learning for vision based grasping

Author(s): Marcos Salganicoff, Lyle H. Ungar, Ruzena Bajcsy
Venue: Machine Learning, 23, 251-278
Year Published: 1996
Keywords: manipulation
Expert Opinion: This work as far as I can detect is the first introducing Active learning and Forgetting for the Perception-Action paradigm. It was the PhD thesis of Marcos Salganicoff in 1992. The paper (in fact several papers) cited here was published later. The new approach allowed the learner to control when and where in the input space the new examples should be gathered. It balances the cost of gathering the experiences (Exploration) with the cost of misclassification and the execution of the task (Exploitation ).

square root sam: simultaneous localization and mapping via square root information smoothing

Author(s): Frank Dellaert, Michael Kaess
Venue: Intl. J. of Robotics Research
Year Published: 2006
Keywords: manipulation, planning, mobile robots, state estimation, visual perception, probabilistic models
Expert Opinion: This paper, as well as the follow up iSAM2 paper, focuses on treating localization and mapping problems as nonlinear least squares and then optimizing as efficiently as possible. This is a powerful technique that serves as the backbone for many SAM solvers, and, can be applied more generally to all sorts of inference problems in robotics. Techniques building on this work have been used in planning, manipulation, and control.

learning attractor landscapes for learning motor primitives

Author(s): Auke Jan Ijspeert, Jun Nakanishi, and Stefan Schaal
Venue: Neural Information Processing Systems Conference (NeurIPS)
Year Published: 2003
Keywords: manipulation, planning, learning from demonstration, reinforcement learning, humanoid robotics
Expert Opinion: Dynamical Movement Primitives have definitely been very influential in mainly learning from demonstration studies. They encode the demonstrated trajectory as a set of differential equations, and offers advantages such as one-shot learning of non-linear movements, real-time stability and robustness under perturbations with guarantees in reaching the goal state, generalization of the movement for different goals, and linear combination of parameters. DMPs can be easily extended with additional terms: e.g. memorized force and tactile profiles can be utilized in modulating learned movement primitives in difficult manipulation tasks that contain high degrees of noise in perception or actuation. DMPs are further intuitive, easy to understand and implement; and therefore have been widely used.

robotic grasping of novel objects using vision

Author(s): Ashutosh Saxena, Justin Driemeyer, Andrew Y. Ng
Venue: International Journal of Robotics Research
Year Published: 2008
Keywords: neural networks, dynamical systems, visual perception, learning from demonstration, manipulation, planning
Expert Opinion: One of the first papers using general visual features for grasping

supersizing self-supervision: learning to grasp from 50k tries and 700 robot hours

Author(s): Lerrel Pinto, Abhinav Gupta
Venue: IEEE International Conference on Robotics and Automation (ICRA)
Year Published: 2015
Keywords: manipulation, reinforcement learning, neural networks
Expert Opinion: Pinto et al., were the first paper to exploit deep learning techniques to process large amounts of data collected by a robot running 24x7 for significantly improving the grasping accuracy without making any object specific assumptions or requiring 3D models of objects. This paper inspired several works in using large scale data to learn intuitive physics, manipulation of deformable objects and also impressive grasping works such as Google's arm farm and DexNet.

an autonomous manipulation system based on force control and optimization

Author(s): Ludovic Righetti, Mrinal Kalakrishnan, Peter Pastor, Jonathan Binney, Jonathan Kelly, Randolph C. Voorhies, Gaurav Sukhatme, Stefan Schaal
Venue: Autonomous Robots Journal
Year Published: 2014
Keywords: manipulation, planning
Expert Opinion: This paper presents a comprehensive description of a complete system architecture for autonomous manipulation of challenging objects covering from low-level control, sensing and calibration to high-level planning and behavior generation. This paper experimentally demonstrates robust and competitive performance in a wide variety of manipulation tasks on robot hardware in a real-world situation.

belief space planning assuming maximum likelihood observations

Author(s): Robert Platt Jr., Russ Tedrake, Leslie Kaelbling, Tomas Lozano-Perez
Venue: Robotics: Science and Systems VI
Year Published: 2010
Keywords: manipulation, dynamical systems, planning, gaussians
Expert Opinion: This isn't a learning paper, but a planning paper. Nonetheless, I feel the need to include it, as it strongly influenced my thinking about manipulation learning. It was the first work that I had seen make POMDPs work for real robotics problems. It teaches students that reasoning about uncertainty is important, but that you need to make the right assumptions in order to make it work for any reasonably sized problem. Whereas PILCO aims to reduce model uncertainty, this work assumes a correct model and leverages information-gathering actions to reduce state uncertainty. Thus, these papers are complementary when discussing uncertainty.

closing the sim-t-real loop: adapting simulation randomization with real world experience

Author(s): Y. Chebotar, A. Handa, V. Makoviychuk, M. Macklin, J. Issac, N. Ratliff, and D. Fox
Venue: IEEE International Conference on Robotics and Automation (ICRA)
Year Published: 2019
Keywords: reinforcement learning, policy gradients, manipulation
Expert Opinion: There are more than one way to view to this work. One, presented in the paper, is to close the sim2real gap by tuning a parametric simulator. Another is to embed a simulation model in the policy representation and close the loop through online learning.

everyday robotic action: lessons from human action control

Author(s): Roy de Kleijn, George Kachergis, Bernhard Hommel
Venue: Frontiers in NeuroRobotics
Year Published: 2014
Keywords: planning, manipulation
Expert Opinion: Roboticists are not the only researchers working on motion representation and generation. Researchers on human motor control approach the problem from a different angle, and their work has often served as an inspiration for me. This paper provides a very nice, easy to understand overview of some topics in the field of human action control, with many interesting citations to follow up.

probabilistic movement primitives

Author(s): Alexandros Paraschos, Christian Daniel, Jan Peters, and Gerhard Neumann
Venue: Neural Information Processing Systems Conference (NeurIPS)
Year Published: 2013
Keywords: manipulation, probabilistic models, gaussians, planning, learning from demonstration
Expert Opinion: This work proposes a probabilistic movement primitive representation that can be trained through least squares regression from demonstrations. The most important feature of this model is its ability to model coupled systems. Thus, through exploiting the learned covariance between limbs or other dimensions whole body motion can be completed and predicted. Also the approach provides a closed form solution of optimal feedback controller in each time step assuming local Gaussian models.

learning to control a low-cost manipulator using data-efficient reinforcement learning

Author(s): Marc Peter Deisenroth, Carl Edward Rasmussen, Dieter Fox
Venue: Robotics: Science and Systems VII
Year Published: 2011
Keywords: manipulation, reinforcement learning, probabilistic models, locomotion, planning, gaussians
Expert Opinion: While this was not the first nor the last publication from Deisenroth and colleagues on PILCO (probabilistic inference for learning control), this is the paper that I remember my colleagues talking about that led me to learn about the approach. This paper was prescient bringing our attention to, and attempting to address, a number of problems in robot learning that still remain important today: data-efficient learning and transfer between related tasks. This paper has a had lasting impact on the field forming the basis of other impressive works in areas of robotics ranging from manipulation to learning underwater swimming gaits.

reinforcement learning of motor skills with policy gradients

Author(s): Jan Peters, Stefan Schaal
Venue: Robotics and Neuroscience
Year Published: 2008
Keywords: manipulation, policy gradients, reinforcement learning, dynamical systems
Expert Opinion: This paper presents some of the early method to learn high-dimensional parameters, which is important in robot manipulation. It presents a non-trivial combination of the authors' earlier work in learning motor skills, that aside from learning how reinforcement learning can be used to learn high-dimensional parameters, it also provide a good short summary of relevant work (up to that point).

end-to-end training of deep visuomotor policies

Author(s): Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel
Venue: Journal of Machine Learning Research
Year Published: 2016
Keywords: manipulation, probabilistic models, planning, locomotion, learning from demonstration, reinforcement learning, neural networks, visual perception
Expert Opinion: This paper uses deep reinforcement learning to get a PR2 to pretty robustly hang a coat hanger on a clothes rack, insert a block into a shape sorting cube, fit the claw of a toy hammer under a nail, and screw on a bottle cap. There were no prior demonstrations used, the resulting network takes in raw camera images and outputs robot motor torques directly, and each task took less than 300 learning trials to train. Especially given how wobbly/inaccurate PR2 arms are, that is quite impressive.

hindsight experience replay

Author(s): Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba
Venue: Neural Information Processing Systems Conference (NeurIPS)
Year Published: 2018
Keywords: manipulation, humanoid robotics, reinforcement learning, neural networks
Expert Opinion: HER addresses the issue of sample inefficiency in DRL, especially for those problems with sparse and binary reward functions. It has become one of the most effective algorithms for learning problems with multiple goals which have the potential to solve many challenging manipulation tasks. The idea of "EVERY experience is a good experience for SOME task" is a powerful insight that succinctly reflects how we teach our children to be lifelong learners. We should teach our robots the same way.

grounding semantic categories in behavioral interactions: experiments with 100 objects

Author(s): Jivko Sinapov, Connor Schenck, Kerrick Staley, Vladimir Sukhoy, Alexander Stoytchev
Venue: Robotics and Autonomous Systems
Year Published: 2012
Keywords: visual perception, manipulation
Expert Opinion: Interactive perception and multimodal sensing are fundamental aspects of robotics and robot learning. The ability to execute actions to interact with the environment provides robots with a rich source of information, especially when combined with haptic, vision, and audio feedback. Grounding the object representations in the robot's actions provides the robot with representations that are not only well suited for future manipulation tasks, but that the robot can estimate through autonomous experimentation. The paper also touches on actively selecting actions to quickly reduce uncertainty.

a review of robot learning for manipulation: challenges, representations, and algorithms

Author(s): Oliver Kroemer, Scott Niekum, George Konidaris
Venue: arXiv
Year Published: 2019
Keywords: survey, probabilistic models, manipulation, reinforcement learning
Expert Opinion: This paper present an incredibly extensive recent survey on learning in robot manipulation (440 citations!!). Surveys are always use especially for new grad students. This one presents a single framework to formalise the robot manipulation problem.

qt-opt: scalable deep reinforcement learning for vision-based robotic manipulation

Author(s): Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, Sergey Levine
Venue: conference on robot learning
Year Published: 2018
Keywords: reinforcement learning, manipulation, neural networks
Expert Opinion: The paper shows that replay buffer based RL methods can be successfully applied to large scale robotic applications. We will see more of this kind of work in the future.

data-driven grasp synthesis-a survey

Author(s): Jeannette Bohg, Antonio Morales, Tamim Asfour, Member, Danica Kragic
Venue: IEEE Transactions on Robotics (Volume 30, Issue 2)
Year Published: 2016
Keywords: survey, visual perception, manipulation
Expert Opinion: A must read for anyone interested in grasping. Great survey on data-driving methods for grasping of, both known and unknown, objects; plus a review and connections to 'traditional' analytical methods!

robotic grasping of novel objects

Author(s): Ashutosh Saxena, Justin Driemeyer, Justin Kearns, Andrew Y. Ng
Venue: Advances in Neural Information Processing Systems
Year Published: 2007
Keywords: manipulation
Expert Opinion: This has been seminal work which showed that object grasping can be learned in a supervised manner from labeled training images. It spawned a string of work in this area culminating in current approaches that use entire robot farms to collect training data.

learning grasping points with shape context

Author(s): Jeannette Bohg, Danica Kragic
Venue: International Conference on Advanced Robotics
Year Published: 2009
Keywords: planning, manipulation, visual perception
Expert Opinion: This is one of the first works in literature that utilized machine learning for the robotic manipulation problem. The proposed framework is still useful to design similar robot learning solutions. The particular importance of this work is to use a global representation of a target object (goal) for manipulation planning