1 code implementation • 26 Mar 2024 • Robert Platt, Rossella Arcucci, Cédric John
Hyperspectral data acquired by the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) have allowed for unparalleled mapping of the surface mineralogy of Mars.
no code implementations • 22 Jan 2024 • Haojie Huang, Owen Howell, Dian Wang, Xupeng Zhu, Robin Walters, Robert Platt
Many complex robotic manipulation tasks can be decomposed as a sequence of pick and place actions.
no code implementations • 15 Aug 2023 • Haojie Huang, Dian Wang, Arsh Tangri, Robin Walters, Robert Platt
This paper analytically studies the symmetries present in planar robotic pick and place and proposes a method of incorporating equivariant neural models into Transporter Net in a way that captures all symmetries.
no code implementations • 21 Jun 2023 • Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi, Abhinav Kumar, Elise van der Pol, Robin Walters, Thomas Kipf, Jan-Willem van de Meent, Lawson L. S. Wong, Robert Platt
We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration.
1 code implementation • 10 Jun 2023 • Xupeng Zhu, Dian Wang, Guanang Su, Ondrej Biza, Robin Walters, Robert Platt
Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware.
1 code implementation • 27 Feb 2023 • David M. Klee, Ondrej Biza, Robert Platt, Robin Walters
Predicting the pose of objects from a single image is an important but difficult computer vision problem.
no code implementations • 16 Nov 2022 • Dian Wang, Jung Yeon Park, Neel Sortur, Lawson L. S. Wong, Robin Walters, Robert Platt
Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network architecture.
1 code implementation • 3 Nov 2022 • Hai Nguyen, Andrea Baisero, Dian Wang, Christopher Amato, Robert Platt
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information.
Partially Observable Reinforcement Learning reinforcement-learning +1
no code implementations • 31 Oct 2022 • Haojie Huang, Dian Wang, Xupeng Zhu, Robin Walters, Robert Platt
Given point cloud input, the problem of 6-DoF grasp pose detection is to identify a set of hand poses in SE(3) from which an object can be successfully grasped.
no code implementations • 18 Jul 2022 • David Klee, Ondrej Biza, Robert Platt, Robin Walters
In this paper, we propose a novel architecture based on icosahedral group convolutions that reasons in $\mathrm{SO(3)}$ by learning a projection of the input image onto an icosahedron.
1 code implementation • 29 Jun 2022 • Colin Kohler, Robert Platt
By combining the LDM with model-free policy learning, we can learn policies which can solve complex manipulation tasks using one-step lookahead planning.
1 code implementation • 2 Jun 2022 • Kevin Esslinger, Robert Platt, Christopher Amato
Such tasks typically require some form of memory, where the agent has access to multiple past observations, in order to perform well.
Partially Observable Reinforcement Learning reinforcement-learning +1
1 code implementation • 27 Apr 2022 • Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong, Thomas Kipf
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
1 code implementation • 10 Feb 2022 • Ondrej Biza, Thomas Kipf, David Klee, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
In this paper, we learn to generalize over robotic pick-and-place tasks using object-factored world models, which combat the combinatorial explosion by ensuring that predictions are equivariant to permutations of objects.
no code implementations • 20 Jan 2022 • Haojie Huang, ZiYi Yang, Robert Platt
Shape completion, the problem of inferring the complete geometry of an object given a partial point cloud, is an important problem in robotics and computer vision.
no code implementations • 29 Sep 2021 • Xupeng Zhu, Dian Wang, Ondrej Biza, Robert Platt
Visual grasp detection is a key problem in robotics where the agent must learn to model the grasp function, a mapping from an image of a scene onto a set of feasible grasp poses.
1 code implementation • 11 Jan 2021 • Ondrej Biza, Dian Wang, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks.
1 code implementation • 19 Oct 2020 • Hai Nguyen, Brett Daley, Xinchao Song, Christopher Amato, Robert Platt
Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state.
1 code implementation • 15 Oct 2020 • Marcus Gualtieri, Robert Platt
One approach is (a) use object instance segmentation and shape completion to model the objects and (b) use a regrasp planner to decide grasps and places displacing the models to their goals.
Robotics
no code implementations • 24 May 2020 • Ulrich Viereck, Kate Saenko, Robert Platt
Learning control policies for visual servoing in novel environments is an important problem.
1 code implementation • pproximateinference AABI Symposium 2021 • Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction.
1 code implementation • 19 Apr 2019 • Marcus Gualtieri, Robert Platt
Learning generalizable skills in robotic manipulation has long been challenging due to real-world sized observation and action spaces.
Robotics
1 code implementation • 30 Nov 2018 • Ondrej Biza, Robert Platt
Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy.
no code implementations • 8 Oct 2018 • Brayan S. Zapata-Impata, Vikrant Shah, Hanumant Singh, Robert Platt
Tasks in outdoor open world environments are now ripe for automation with mobile manipulators.
Robotics
no code implementations • 27 Sep 2018 • Siddharth Mysore, Robert Platt, Kate Saenko
We propose a novel method to exploit this observation to develop robust actor policies, by automatically developing a sampling curriculum over environment settings to use in training.
no code implementations • 27 Jul 2018 • Ulrich Viereck, Xingchao Peng, Kate Saenko, Robert Platt
This paper proposes an approach to domain transfer based on a pairwise loss function that helps transfer control policies learned in simulation onto a real robot.
1 code implementation • 15 Jun 2018 • Marcus Gualtieri, Robert Platt
We address a class of manipulation problems where the robot perceives the scene with a depth sensor and can move its end effector in a space with six degrees of freedom -- 3D position and orientation.
Robotics
no code implementations • ICLR 2019 • Andrew Levy, Robert Platt, Kate Saenko
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse.
Hierarchical Reinforcement Learning reinforcement-learning +1
4 code implementations • 4 Dec 2017 • Andrew Levy, George Konidaris, Robert Platt, Kate Saenko
Hierarchical agents have the potential to solve sequential decision making tasks with greater sample efficiency than their non-hierarchical counterparts because hierarchical agents can break down tasks into sets of subtasks that only require short sequences of decisions.
1 code implementation • 18 Jul 2017 • Marcus Gualtieri, Andreas ten Pas, Robert Platt
Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more abstract formulation.
Robotics
1 code implementation • 29 Jun 2017 • Andreas ten Pas, Marcus Gualtieri, Kate Saenko, Robert Platt
Many grasp detection methods achieve grasp success rates (grasp successes as a fraction of the total number of grasp attempts) between 75% and 95% for novel objects presented in isolation or in light clutter.
Robotics
no code implementations • 14 Jun 2017 • Ulrich Viereck, Andreas ten Pas, Kate Saenko, Robert Platt
This paper proposes an approach to learning a closed-loop controller for robotic grasping that dynamically guides the gripper to the object.
3 code implementations • 4 Mar 2016 • Marcus Gualtieri, Andreas ten Pas, Kate Saenko, Robert Platt
Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network.
Robotics
no code implementations • 13 Jan 2015 • Andreas ten Pas, Robert Platt
Overall, our method achieves an average grasp success rate of 88% when grasping novels objects presented in isolation and an average success rate of 73% when grasping novel objects presented in dense clutter.
Robotics