Ben Eisner
YOU?
Author Swipe
View article: Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement
Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement Open
Long-horizon planning for robot manipulation is a challenging problem that requires reasoning about the effects of a sequence of actions on a physical 3D scene. While traditional task planning methods are shown to be effective for long-hor…
View article: FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation
FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation Open
We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation mod…
View article: Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks Open
Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is define…
View article: On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks
On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks Open
While solving complex manipulation tasks, manipulation policies often need to learn a set of diverse skills to accomplish these tasks. The set of skills is often quite multimodal - each one may have a quite distinct distribution of actions…
View article: FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection
FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection Open
Understanding and manipulating articulated objects, such as doors and drawers, is crucial for robots operating in human environments. We wish to develop a system that can learn to articulate novel objects with no prior interaction, after t…
View article: TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation Open
How do we imbue robots with the ability to efficiently manipulate unseen objects and transfer relevant skills based on demonstrations? End-to-end learning methods often fail to generalize to novel objects or unseen configurations. Instead,…
View article: FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects
FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects Open
We explore a novel method to perceive and manipulate 3D articulated objects that generalizes to enable a robot to articulate unseen classes of objects. We propose a vision-based system that learns to predict the potential motions of the pa…
View article: Self-supervised Transparent Liquid Segmentation for Robotic Pouring
Self-supervised Transparent Liquid Segmentation for Robotic Pouring Open
Liquid state estimation is important for robotics tasks such as pouring; however, estimating the state of transparent liquids is a challenging problem. We propose a novel segmentation pipeline that can segment transparent liquids such as w…
View article: Reward Prediction Error as an Exploration Objective in Deep RL
Reward Prediction Error as an Exploration Objective in Deep RL Open
A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek n…
View article: Robotic Grasping through Combined Image-Based Grasp Proposal and 3D Reconstruction
Robotic Grasping through Combined Image-Based Grasp Proposal and 3D Reconstruction Open
We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network. Our system generates 6-DOF grasps from a single RGB-D image of the target object, which is pro…
View article: Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction Open
We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network. Our system generates 6-DOF grasps from a single RGB-D image of the target object, which is pro…
View article: Pixels to Plans: Learning Non-Prehensile Manipulation by Imitating a Planner
Pixels to Plans: Learning Non-Prehensile Manipulation by Imitating a Planner Open
We present a novel method enabling robots to quickly learn to manipulate objects by leveraging a motion planner to generate "expert" training trajectories from a small amount of human-labeled data. In contrast to the traditional sense-plan…
View article: QXplore: Q-Learning Exploration by Maximizing Temporal Difference Error
QXplore: Q-Learning Exploration by Maximizing Temporal Difference Error Open
A major challenge in reinforcement learning is exploration, especially when
reward landscapes are sparse. Several recent methods provide an intrinsic
motivation to explore by directly encouraging agents to seek novel states. A
potential di…
View article: Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
Q-Learning for Continuous Actions with Cross-Entropy Guided Policies Open
Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods are consequently intractable. Standard methods for applying…
View article: emoji2vec: Learning Emoji Representations from their Description
emoji2vec: Learning Emoji Representations from their Description Open
Many current natural language processing applications for social media rely on representation learning and utilize pre-trained word embeddings. There currently exist several publicly-available, pre-trained sets of word embeddings, but they…
View article: emoji2vec: Learning Emoji Representations from their Description
emoji2vec: Learning Emoji Representations from their Description Open
Many current natural language processing applications for social media rely on representation learning and utilize pre-trained word embeddings. There currently exist several publicly-available, pre-trained sets of word embeddings, but they…