Peter K. Allen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peter K. Allen has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Iretiayo Akinola
Robotics Lab, Columbia University, New York, USA
3 shared publications Bohan Wu
Columbia University New York NY United States
2 shared publications- Hao Dang
Columbia University
2 shared publications - Jacob Varley
Robotics at Google, New York, USA
2 shared publications - Abhi Gupta
Robotics Lab, Columbia University, New York, USA
1 shared publication Adam Richardson
1 shared publication
Latest Publications
- Open Access
Teleoperated Robot Grasping in Virtual Reality Spaces
Despite recent advancement in virtual reality technology, teleoperating a high DoF robot to complete dexterous tasks in cluttered scenes remains difficult. In this work, we propose a system that allows the user to teleoperate a Fetch robot to perform grasping in an easy and intuitive way, through exploiting the rich environment information provided by the virtual reality space. Our system has the benefit of easy transferability to different robots and different tasks, and can be used without any expert knowledge. We tested the system on a real fetch robot, and a video demonstrating the effectiveness of our system can be seen at https://youtu.be/1-xW2Bx_Cms.
Open AccessTeleoperated Robot Grasping in Virtual Reality Spaces
Despite recent advancement in virtual reality technology, teleoperating a high DoF robot to complete dexterous tasks in cluttered scenes remains difficult. In this work, we propose a system that allows the user to teleoperate a Fetch robot to perform grasping in an easy and intuitive way, through exploiting the rich environment information provided by the virtual reality space. Our system has the benefit of easy transferability to different robots and different tasks, and can be used without any expert knowledge. We tested the system on a real fetch robot, and a video demonstrating the effectiveness of our system can be seen at https://youtu.be/1-xW2Bx_Cms.
- Open Access
Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation
We present a robot navigation system that uses an imitation learning framework to successfully navigate in complex environments. Our framework takes a pre-built 3D scan of a real environment and trains an agent from pre-generated expert trajectories to navigate to any position given a panoramic view of the goal and the current visual input without relying on map, compass, odometry, or relative position of the target at runtime. Our end-to-end trained agent uses RGB and depth (RGBD) information and can handle large environments (up to $1031m^2$) across multiple rooms (up to $40$) and generalizes to unseen targets. We show that when compared to several baselines our method (1) requires fewer training examples and less training time, (2) reaches the goal location with higher accuracy, and (3) produces better solutions with shorter paths for long-range navigation tasks.
Open AccessLearning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation
We present a robot navigation system that uses an imitation learning framework to successfully navigate in complex environments. Our framework takes a pre-built 3D scan of a real environment and trains an agent from pre-generated expert trajectories to navigate to any position given a panoramic view of the goal and the current visual input without relying on map, compass, odometry, or relative position of the target at runtime. Our end-to-end trained agent uses RGB and depth (RGBD) information and can handle large environments (up to $1031m^2$) across multiple rooms (up to $40$) and generalizes to unseen targets. We show that when compared to several baselines our method (1) requires fewer training examples and less training time, (2) reaches the goal location with higher accuracy, and (3) produces better solutions with shorter paths for long-range navigation tasks.
- 20 February 2020
- Published by Springer Nature in Autonomous Robots
- Vol. 44 (6) , 971-990
Generative Attention Learning: a “GenerAL” framework for high-performance multi-fingered grasping in clutter
- 20 February 2020
- Published by Springer Nature in Autonomous Robots
- Vol. 44 (6) , 971-990
Generative Attention Learning: a “GenerAL” framework for high-performance multi-fingered grasping in clutter
- Open Access
MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery from a failed grasp is further complicated by visual occlusion, as the hand is usually occluding the vision sensor as it attempts another open-loop regrasp. This work presents MAT, a tactile closed-loop method capable of realizing grasps provided by a coarse initial positioning of the hand above an object. Our algorithm is a deep reinforcement learning (RL) policy optimized through the clipped surrogate objective within a maximum entropy RL framework to balance exploitation and exploration. The method utilizes tactile and proprioceptive information to act through both fine finger motions and larger regrasp movements to execute stable grasps. A novel curriculum of action motion magnitude makes learning more tractable and helps turn common failure cases into successes. Careful selection of features that exhibit small sim-to-real gaps enables this tactile grasping policy, trained purely in simulation, to transfer well to real world environments without the need for additional learning. Experimentally, this methodology improves over a vision-only grasp success rate substantially on a multi-fingered robot hand. When this methodology is used to realize grasps from coarse initial positions provided by a vision-only planner, the system is made dramatically more robust to calibration errors in the camera-robot transform.
Open AccessMAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery from a failed grasp is further complicated by visual occlusion, as the hand is usually occluding the vision sensor as it attempts another open-loop regrasp. This work presents MAT, a tactile closed-loop method capable of realizing grasps provided by a coarse initial positioning of the hand above an object. Our algorithm is a deep reinforcement learning (RL) policy optimized through the clipped surrogate objective within a maximum entropy RL framework to balance exploitation and exploration. The method utilizes tactile and proprioceptive information to act through both fine finger motions and larger regrasp movements to execute stable grasps. A novel curriculum of action motion magnitude makes learning more tractable and helps turn common failure cases into successes. Careful selection of features that exhibit small sim-to-real gaps enables this tactile grasping policy, trained purely in simulation, to transfer well to real world environments without the need for additional learning. Experimentally, this methodology improves over a vision-only grasp success rate substantially on a multi-fingered robot hand. When this methodology is used to realize grasps from coarse initial positions provided by a vision-only planner, the system is made dramatically more robust to calibration errors in the camera-robot transform.
- Open Access
Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of algorithms in multi-fingered robotic grasping remains a challenge due to large sim-to-real fidelity gaps and the high sample complexity of on-policy RL algorithms. This work aims to bridge these gaps by first reinforcement-learning a multi-fingered robotic grasping policy in simulation that operates in the pixel space of the input: a single depth image. Using a mapping from pixel space to Cartesian space according to the depth map, this method transfers to the real world with high fidelity and introduces a novel attention mechanism that substantially improves grasp success rate in cluttered environments. Finally, the direct-generative nature of this method allows learning of multi-fingered grasps that have flexible end-effector positions, orientations and rotations, as well as all degrees of freedom of the hand.
Open AccessPixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of algorithms in multi-fingered robotic grasping remains a challenge due to large sim-to-real fidelity gaps and the high sample complexity of on-policy RL algorithms. This work aims to bridge these gaps by first reinforcement-learning a multi-fingered robotic grasping policy in simulation that operates in the pixel space of the input: a single depth image. Using a mapping from pixel space to Cartesian space according to the depth map, this method transfers to the real world with high fidelity and introduces a novel attention mechanism that substantially improves grasp success rate in cluttered environments. Finally, the direct-generative nature of this method allows learning of multi-fingered grasps that have flexible end-effector positions, orientations and rotations, as well as all degrees of freedom of the hand.
- 27 July 2017
- Published by Springer Nature
- p. 325-340
Grasping with Your Brain: A Brain-Computer Interface for Fast Grasp Selection
- 27 July 2017
- Published by Springer Nature
- p. 325-340
Grasping with Your Brain: A Brain-Computer Interface for Fast Grasp Selection
- Open Access
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 34, 547-554
Capture, learning, and classification of upper extremity movement primitives in healthy controls and stroke patients
There currently exist no practical tools to identify functional movements in the upper extremities (UEs). This absence has limited the precise therapeutic dosing of patients recovering from stroke. In this proof-of-principle study, we aimed to develop an accurate approach for classifying UE functional movement primitives, which comprise functional movements. Data were generated from inertial measurement units (IMUs) placed on upper body segments of older healthy individuals and chronic stroke patients. Subjects performed activities commonly trained during rehabilitation after stroke. Data processing involved the use of a sliding window to obtain statistical descriptors, and resulting features were processed by a Hidden Markov Model (HMM). The likelihoods of the states, resulting from the HMM, were segmented by a second sliding window and their averages were calculated. The final predictions were mapped to human functional movement primitives using a Logistic Regression algorithm. Algorithm performance was assessed with a leave-one-out analysis, which determined its sensitivity, specificity, and positive and negative predictive values for all classified primitives. In healthy control and stroke participants, our approach identified functional movement primitives embedded in training activities with, on average, 80% precision. This approach may support functional movement dosing in stroke rehabilitation.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 34, 547-554
Open AccessCapture, learning, and classification of upper extremity movement primitives in healthy controls and stroke patients
There currently exist no practical tools to identify functional movements in the upper extremities (UEs). This absence has limited the precise therapeutic dosing of patients recovering from stroke. In this proof-of-principle study, we aimed to develop an accurate approach for classifying UE functional movement primitives, which comprise functional movements. Data were generated from inertial measurement units (IMUs) placed on upper body segments of older healthy individuals and chronic stroke patients. Subjects performed activities commonly trained during rehabilitation after stroke. Data processing involved the use of a sliding window to obtain statistical descriptors, and resulting features were processed by a Hidden Markov Model (HMM). The likelihoods of the states, resulting from the HMM, were segmented by a second sliding window and their averages were calculated. The final predictions were mapped to human functional movement primitives using a Logistic Regression algorithm. Algorithm performance was assessed with a leave-one-out analysis, which determined its sensitivity, specificity, and positive and negative predictive values for all classified primitives. In healthy control and stroke participants, our approach identified functional movement primitives embedded in training activities with, on average, 80% precision. This approach may support functional movement dosing in stroke rehabilitation.
- Open Access
Shape Completion Enabled Robotic Grasping
This work provides an architecture to enable robotic grasp planning via shape completion. Shape completion is accomplished through the use of a 3D convolutional neural network (CNN). The network is trained on our own new open source dataset of over 440,000 3D exemplars captured from varying viewpoints. At runtime, a 2.5D pointcloud captured from a single point of view is fed into the CNN, which fills in the occluded regions of the scene, allowing grasps to be planned and executed on the completed object. Runtime shape completion is very rapid because most of the computational costs of shape completion are borne during offline training. We explore how the quality of completions vary based on several factors. These include whether or not the object being completed existed in the training data and how many object models were used to train the network. We also look at the ability of the network to generalize to novel objects allowing the system to complete previously unseen objects at runtime. Finally, experimentation is done both in simulation and on actual robotic hardware to explore the relationship between completion quality and the utility of the completed mesh model for grasping.
Open AccessShape Completion Enabled Robotic Grasping
This work provides an architecture to enable robotic grasp planning via shape completion. Shape completion is accomplished through the use of a 3D convolutional neural network (CNN). The network is trained on our own new open source dataset of over 440,000 3D exemplars captured from varying viewpoints. At runtime, a 2.5D pointcloud captured from a single point of view is fed into the CNN, which fills in the occluded regions of the scene, allowing grasps to be planned and executed on the completed object. Runtime shape completion is very rapid because most of the computational costs of shape completion are borne during offline training. We explore how the quality of completions vary based on several factors. These include whether or not the object being completed existed in the training data and how many object models were used to train the network. We also look at the ability of the network to generalize to novel objects allowing the system to complete previously unseen objects at runtime. Finally, experimentation is done both in simulation and on actual robotic hardware to explore the relationship between completion quality and the utility of the completed mesh model for grasping.
- Open Access
Toward a Science of Autonomy for Physical Systems: Service
A recent study by the Robotic Industries Association has highlighted how service robots are increasingly broadening our horizons beyond the factory floor. From robotic vacuums, bomb retrievers, exoskeletons and drones, to robots used in surgery, space exploration, agriculture, home assistance and construction, service robots are building a formidable resume. In just the last few years we have seen service robots deliver room service meals, assist shoppers in finding items in a large home improvement store, checking in customers and storing their luggage at hotels, and pour drinks on cruise ships. Personal robots are here to educate, assist and entertain at home. These domestic robots can perform daily chores, assist people with disabilities and serve as companions or pets for entertainment. By all accounts, the growth potential for service robotics is quite large.
Open AccessToward a Science of Autonomy for Physical Systems: Service
A recent study by the Robotic Industries Association has highlighted how service robots are increasingly broadening our horizons beyond the factory floor. From robotic vacuums, bomb retrievers, exoskeletons and drones, to robots used in surgery, space exploration, agriculture, home assistance and construction, service robots are building a formidable resume. In just the last few years we have seen service robots deliver room service meals, assist shoppers in finding items in a large home improvement store, checking in customers and storing their luggage at hotels, and pour drinks on cruise ships. Personal robots are here to educate, assist and entertain at home. These domestic robots can perform daily chores, assist people with disabilities and serve as companions or pets for entertainment. By all accounts, the growth potential for service robotics is quite large.
- Open Access
Articulated Pose Estimation Using Hierarchical Exemplar-Based Models
Exemplar-based models have achieved great success on localizing the parts of semi-rigid objects. However, their efficacy on highly articulated objects such as humans is yet to be explored. Inspired by hierarchical object representation and recent application of Deep Convolutional Neural Networks (DCNNs) on human pose estimation, we propose a novel formulation that incorporates both hierarchical exemplar-based models and DCNNs in the spatial terms. Specifically, we obtain more expressive spatial models by assuming independence between exemplars at different levels in the hierarchy; we also obtain stronger spatial constraints by inferring the spatial relations between parts at the same level. As our method strikes a good balance between expressiveness and strength of spatial models, it is both effective and generalizable, achieving state-of-the-art results on different benchmarks: Leeds Sports Dataset and CUB-200-2011.
Open AccessArticulated Pose Estimation Using Hierarchical Exemplar-Based Models
Exemplar-based models have achieved great success on localizing the parts of semi-rigid objects. However, their efficacy on highly articulated objects such as humans is yet to be explored. Inspired by hierarchical object representation and recent application of Deep Convolutional Neural Networks (DCNNs) on human pose estimation, we propose a novel formulation that incorporates both hierarchical exemplar-based models and DCNNs in the spatial terms. Specifically, we obtain more expressive spatial models by assuming independence between exemplars at different levels in the hierarchy; we also obtain stronger spatial constraints by inferring the spatial relations between parts at the same level. As our method strikes a good balance between expressiveness and strength of spatial models, it is both effective and generalizable, achieving state-of-the-art results on different benchmarks: Leeds Sports Dataset and CUB-200-2011.