Search Results for author:
Found 107 papers, 37 papers with code
RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations
Imitation learning in robotics faces significant challenges in generalization due to the complexity of robotic environments and the high cost of data collection.
DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation
A key factor in our success is a smooth contact model that combines informative gradients with physical accuracy, ensuring effective transfer of learned behaviors.
SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation
We find that SPIRE outperforms prior approaches that integrate imitation learning, reinforcement learning, and planning by 35% to 50% in average task performance, is 6 times more data efficient in the number of human demonstrations needed to train proficient agents, and learns to complete tasks nearly twice as efficiently.
CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building
Intelligent and reliable task planning is a core capability for generalized robotics, requiring a descriptive domain representation that sufficiently models all object and state information for the scene.
PWM: Policy Learning with Large World Models
Reinforcement Learning (RL) has achieved impressive results on complex tasks but struggles in multi-task settings with different embodiments.
Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation
Model-Free Reinforcement Learning (MFRL), leveraging the policy gradient theorem, has demonstrated considerable success in continuous control tasks.
Composable Part-Based Manipulation
In this paper, we propose composable part-based manipulation (CPM), a novel approach that leverages object-part decomposition and part-part correspondences to improve learning and generalization of robotic manipulation skills.
AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
Encouraged by the remarkable achievements of language and vision foundation models, developing generalist robotic agents through imitation learning, using large demonstration datasets, has become a prominent area of interest in robot learning.
Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications
Safe reinforcement learning tasks are a challenging domain despite being very common in the real world.
ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization
Despite the many benefits incurred by the integration of advanced and special-purpose lab equipment, many aspects of experimentation are still manually conducted by chemists, for example, polishing an electrode in electrochemistry experiments.
Benchmarks for Physical Reasoning AI
Therefore, we aim to offer an overview of existing benchmarks and their solution approaches and propose a unified perspective for measuring the physical reasoning capacity of AI systems.
HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors
We demonstrate that HandyPriors attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement.
Self-Supervised Learning of Action Affordances as Interaction Modes
We show in the experiments that such affordance learning predicts interaction which covers most modes of interaction for the querying articulated object and can be fine-tuned to a goal-conditional model.
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Finally, we demonstrate the scalability of SlotDiffusion to unconstrained real-world datasets such as PASCAL VOC and COCO, when integrated with self-supervised pre-trained image encoders.
Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
We propose Structured Exploration with Achievements (SEA), a multi-stage reinforcement learning algorithm designed for achievement-based environments, a particular type of environment with an internal achievement set.
StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos
This motivates the need to temporally localize the instruction steps in such videos, i. e. the task called key-step localization.
$Δ$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss
Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time.
MVTrans: Multi-View Perception of Transparent Objects
Transparent object perception is a crucial skill for applications such as robot manipulation in household and laboratory settings.
Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
We present Orbit, a unified and modular framework for robot learning powered by NVIDIA Isaac Sim.
Offline Policy Optimization in RL with Variance Regularizaton
Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications.
NeurIPS 2022 Competition: Driving SMARTS
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
nerf2nerf: Pairwise Registration of Neural Radiance Fields
We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i. e. ICP) to operate on Neural Radiance Fields (NeRF) -- neural 3D scene representations trained from collections of calibrated images.
MoCoDA: Model-based Counterfactual Data Augmentation
To this end, we show that (1) known local structure in the environment transitions is sufficient for an exponential reduction in the sample complexity of training a dynamics model, and (2) a locally factored dynamics model provably generalizes out-of-distribution to unseen states and actions.
Breaking Bad: A Dataset for Geometric Fracture and Reassembly
We introduce Breaking Bad, a large-scale dataset of fractured objects.
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
While recent object-centric models can successfully decompose a scene into objects, modeling their dynamics effectively still remains a challenge.
See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction
Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors.
ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information.
Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions
The pipeline of current robotic pick-and-place methods typically consists of several stages: grasp pose detection, finding inverse kinematic solutions for the detected poses, planning a collision-free trajectory, and then executing the open-loop trajectory to the grasp pose with a low-level tracking controller.
SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments
Traditional biological and pharmaceutical manufacturing plants are controlled by human workers or pre-defined thresholds.
Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors
While the majority of existing part assembly methods focus on correctly posing semantic parts to recreate a whole object, we interpret assembly more literally: as mating geometric parts together to achieve a snug fit.
Accelerated Policy Learning with Parallel Differentiable Simulation
In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effectively leverage simulation gradients, even in the presence of non-smoothness.
Value Gradient weighted Model-Based Reinforcement Learning
However, they tend to be inferior in practice to commonly used maximum likelihood (MLE) based approaches.
Model-based Reinforcement Learning
reinforcement-learning
+2
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos.
Ranked #17 on
Video Retrieval
on LSMDC
(using extra training data)
DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting
In this work, we present DiSECt: the first differentiable simulator for cutting soft materials.
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning
We show that such OOD sampling and pessimistic bootstrapping yields provable uncertainty quantifier in linear MDPs, thus providing the theoretical underpinning for PBRL.
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
The learned policies may then be deployed in real-world settings where interactions are costly or dangerous.
Ranked #1 on
Offline RL
on D4RL
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-intuitive, impractical and often opaque conditions.
Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
We present an extended abstract for the previously published work TESSERACT [Mahajan et al., 2021], which proposes a novel solution for Reinforcement Learning (RL) in large, factored action spaces using tensor decompositions.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Dynamic Bottleneck for Robust Self-Supervised Exploration
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards.
Continuous-Time Fitted Value Iteration for Robust Policies
Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs equation, is important as it yields the optimal policy that achieves the maximum reward on a give task.
Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects
To address the shortcomings of existing transparent object data collection schemes in literature, we also propose an automated dataset creation workflow that consists of robot-controlled image collection and vision-based automatic annotation.
Generalizing Successor Features to continuous domains for Multi-task Learning
In this paper, we consider the problem of continuous control for various robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks, related through the reward function.
Auditing AI models for Verified Deployment under Semantic Specifications
We enable such unit tests through variations in a semantically-interpretable latent space of a generative model.
Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers
In our experiments, we show that Drop-DTW is a robust similarity measure for sequence retrieval and demonstrate its effectiveness as a training loss on diverse applications.
Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger
We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator.
Centralized Model and Exploration Policy for Multi-Agent RL
We also learn a centralized exploration policy within our model that learns to collect additional data in state-action regions with high model uncertainty.
A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution
Natural language provides an accessible and expressive interface to specify long-term tasks for robotic agents.
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes.
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Algorithms derived from Tesseract decompose the Q-tensor across agents and utilise low-rank tensor approximations to model agent interactions relevant to the task.
Robust Value Iteration for Continuous Control Tasks
The adversarial perturbations encourage a optimal policy that is robust to changes in the dynamics.
Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players.
Multi-agent Reinforcement Learning
reinforcement-learning
+4
Principled Exploration via Optimistic Bootstrapping and Backward Induction
In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I).
Value Iteration in Continuous Actions, States and Time
This algorithm enables dynamic programming for continuous states and actions with a known dynamics model.
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot.
LASER: Learning a Latent Action Space for Efficient Reinforcement Learning
Additionally, similar tasks or instances of the same task family impose latent manifold constraints on the most effective action space: the task family can be best solved with actions in a manifold of the entire action space of the robot.
Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation
A kitchen assistant needs to operate human-scale objects, such as cabinets and ovens, in unmapped environments with dynamic obstacles.
S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning
Offline reinforcement learning proposes to learn policies from large collected datasets without interacting with the physical environment.
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathematically, but rather through natural task specification.
Offline Policy Optimization with Variance Regularization
Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications.
A Coach-Player Framework for Dynamic Team Composition
The performance of our method is comparable or even better than the setting where all players have a full view of the environment, but no coach.
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Through experimentation and comparative study, we demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.
Latent Skill Planning for Exploration and Transfer
To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge.
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon.
Modular Action Concept Grounding in Semantic Video Prediction
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects.
Solving Physics Puzzles by Reasoning about Paths
We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal.
Conservative Safety Critics for Exploration
Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still enabling trial and error learning.
D2RL: Deep Dense Architectures in Reinforcement Learning
While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for reinforcement learning remain relatively under-explored.
Action Concept Grounding Network for Semantically-Consistent Video Generation
Recent works in self-supervised video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the problem of semantic learning.
Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago).
OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
We propose a variational inference framework OCEAN to perform online task inference for compositional tasks.
Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter
When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the object of interest and make it graspable.
Counterfactual Data Augmentation using Locally Factored Dynamics
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses.
De-anonymization of authors through arXiv submissions during double-blind review
Under two conditions: papers that are released on arXiv before the review phase and papers that are not, we examine the correlation between the reputation of their authors with the review scores and acceptance decisions.
Causal Discovery in Physical Systems from Videos
We assume access to different configurations and environmental conditions, i. e., data from unknown interventions on the underlying system; thus, we can hope to discover the correct underlying causal graph without explicit interventions.
Uniform Priors for Data-Efficient Transfer
Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge.
Experience Replay with Likelihood-free Importance Weights
The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning.
LEAF: Latent Exploration Along the Frontier
We target the challenging problem of policy learning from initial and goal states specified as images, and do not assume any access to the underlying ground-truth states of the robot and the environment.
Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning
Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state.
Diversity inducing Information Bottleneck in Model Ensembles
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research.
Semi-Supervised StyleGAN for Disentanglement Learning
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation.
Curriculum By Smoothing
We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel.
Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos
However, the reconstruction task of the entire image forces the model to allocate landmarks to model the background.
InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation.
Angular Visual Hardness
We also find that AVH has a statistically significant correlation with human visual hardness.
IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data
For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task.
Motion Reasoning for Goal-Based Imitation Learning
We further show that by using the automatically inferred goal from the video demonstration, our robot is able to reproduce the same task in a real kitchen environment.
Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity
We evaluate the quality of our platform, the diversity of demonstrations in our dataset, and the utility of our dataset via quantitative and qualitative analysis.
A Programmable Approach to Neural Network Compression
Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform.
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
The fundamental challenge of planning for multi-step manipulation is to find effective and plausible action sequences that lead to the task goal.
Disentangled GANs for Controllable Generation of High-Resolution Images
Generative adversarial networks (GANs) have achieved great success at generating realistic samples.
InfoCNF: Efficient Conditional Continuous Normalizing Flow Using Adaptive Solvers
Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation.
Controlling Assistive Robots with Learned Latent Actions
Our insight is that we can make assistive robots easier for humans to control by leveraging latent actions.
Robotics
AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency.
Video Interpolation and Prediction with Unsupervised Landmarks
Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting.
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures.
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback.
Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks
This paper studies the effect of different action spaces in deep RL and advocates for Variable Impedance Control in End-effector Space (VICES) as an advantageous action space for constrained and contact-rich tasks.
Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
In this paper, we formalize Mechanical Search and study a version where distractor objects are heaped over the target object in a bin.
Robotics
RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation
Imitation Learning has empowered recent advances in learning robotic manipulation tasks by addressing shortcomings of Reinforcement Learning such as exploration and reward specification.
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback.
Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it is necessary to explicitly incorporate the compositional structure of the tasks into the model.
Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
We perform both simulated and real-world experiments on two tool-based manipulation tasks: sweeping and hammering.
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
In this work, we propose to tackle this new task with a weakly-supervised framework for reference-aware visual grounding in instructional videos, where only the temporal alignment between the transcription and the video segment are available for supervision.
Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
We explore how Deep Neural Networks can represent meta-policies that switch among a set of previously learned policies, specifically in settings where the dynamics of a new scenario are composed of a mixture of previously learned dynamics and where the state observation is possibly corrupted by sensing noise.
Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction.
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image
We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DeformNet uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DeformNet quantitatively matches or outperforms their benchmarks by significant margins.
Weakly supervised 3D Reconstruction with Adversarial Constraint
Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks.
