All Papers

• 3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
• A User’s Guide to Calibrating Robotic Simulators
• Accelerating Reinforcement Learning with Learned Skill Priors
• ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing
• Action-based Representation Learning for Autonomous Driving
• Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning
• Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity
• Assisted Perception: Optimizing Observations to Communicate State
• Asynchronous Deep Model Reference Adaptive Control
• Attention-Privileged Reinforcement Learning
• Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes
• Augmenting GAIL with BC for sample efficient imitation learning
• Auxiliary Tasks Speed Up Learning PointGoal Navigation
• BayesRace: Learning to race autonomously using prior experience
• Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability
• CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs
• Chaining Behaviors from Data with Model-Free Reinforcement Learning
• CLOUD: Contrastive Learning of Unsupervised Dynamics
• ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations
• Contrastive Variational Reinforcement Learning for Complex Observations
• CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation
• Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space
• Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching
• Deep Reactive Planning in Dynamic Environments
• Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control
• DeepMPCVS: Deep Model Predictive Control for Visual Servoing
• Differentiable Logic Layer for Rule Guided Trajectory Prediction
• DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfer
• Diverse Plausible Shape Completions from Ambiguous Depth Images
• DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning
• EXI-Net: EXplicitly/Implicitly Conditioned Network for Multiple Environment Sim-to-Real Transfer
• Explicitly Encouraging Low Fractional Dimensional Trajectories Via Reinforcement Learning
• Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects
• f-IRL: Inverse Reinforcement Learning via State Marginal Matching
• Fast robust peg-in-hole insertion with continuous visual servoing
• Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following
• Fit2Form: 3D Generative Model for Robot Gripper Form Design
• Flightmare: A Flexible Quadrotor Simulator
• From pixels to legs: Hierarchical learning of quadruped locomotion
• GDN: A Coarse-To-Fine (C2F) Representation for End-To-End 6-DoF Grasp Detection
• Generalization Guarantees for Imitation Learning
• Generation of Realistic Images for Learning in Simulation using FeatureGAN
• Generative adversarial training of product of policies for robust and adaptive movement primitives
• Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
• Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning
• Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
• Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps
• High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards
• Incremental learning of EMG-based control commands using Gaussian Processes
• Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents
• Interactive Imitation Learning in State-Space
• Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting
• Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing
• IV-SLAM: Introspective Vision for Simultaneous Localization and Mapping
• Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning
• Learning 3D Dynamic Scene Representations for Robot Manipulation
• Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
• Learning a Decentralized Multi-Arm Motion Planner
• Learning a Decision Module by Imitating Driver’s Control Behaviors
• Learning a natural-language to LTL executable semantic parser for grounded robotics
• Learning an Expert Skill-Space for Replanning Dynamic Quadruped Locomotion over Obstacles
• Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
• Learning Certified Control Using Contraction Metric
• Learning Dexterous Manipulation from Suboptimal Experts
• Learning Equality Constraints for Motion Planning on Manifolds
• Learning from Demonstrations using Signal Temporal Logic
• Learning from Suboptimal Demonstration via Self-Supervised Reward Regression
• Learning hierarchical relationships for object-goal navigation
• Learning Hierarchical Task Networks with Preferences from Unannotated Demonstrations
• Learning Hybrid Control Barrier Functions from Data
• Learning Interactively to Resolve Ambiguity in Reference Frame Selection
• Learning Latent Representations to Influence Multi-Agent Interaction
• Learning Object Manipulation Skills via Approximate State Estimation from Real Videos
• Learning Object-conditioned Exploration using Distributed Soft Actor Critic
• Learning Obstacle Representations for Neural Motion Planning
• Learning Predictive Models for Ergonomic Control of Prosthetic Devices
• Learning Predictive Representations for Deformable Objects Using Contrastive Estimation
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• Learning rich touch representations through cross-modal self-supervision
• Learning Stability Certificates from Data
• Learning to Communicate and Correct Pose Errors
• Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation
• Learning to Improve Multi-Robot Hallway Navigation
• Learning to Walk in the Real World with Minimal Human Effort
• Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning
• Learning Vision-based Reactive Policies for Obstacle Avoidance
• LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
• Map-Adaptive Goal-Based Trajectory Prediction
• MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control
• MELD: Meta-Reinforcement Learning from Images via Latent State Models
• Model-Based Inverse Reinforcement Learning from Visual Demonstrations
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous
• Modeling Long-horizon Tasks as Sequential Interaction Landscapes
• Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments
• MuGNet: Multi-Resolution Graph Neural Network for Segmenting Large-Scale Pointclouds
• Multi-Level Structure vs. End-to-End-Learning in High-Performance Tactile Robotic Manipulation
• Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments
• Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
• Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
• MultiPoint: Cross-spectral registration of thermal and optical aerial imagery
• Neuro-Symbolic Program Search for Autonomous Driving Decision Module Design
• Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
• One Thousand and One Hours: Self-driving Motion Prediction Dataset
• PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards
• Planning Paths Through Unknown Space by Imagining What Lies Therein
• PLAS: Latent Action Space for Offline Reinforcement Learning
• PLOP: Probabilistic poLynomial Objects trajectory Prediction for autonomous driving
• Policy learning in SE(3) action spaces
• Positive-Unlabeled Reward Learning
• Probably Approximately Correct Vision-Based Planning using Motion Primitives
• Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
• Reactive motion planning with probabilisticsafety guarantees
• Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
• Recovering and Simulating Pedestrians in the Wild
• Reinforcement Learning with Videos: Combining Offline Observations with Interaction
• Relational Learning for Skill Preconditions
• Robot Action Selection Learning via Layered Dimension Informed Program Synthesis
• Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
• Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach
• ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning
• S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds
• S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
• Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
• Safe Policy Learning for Continuous Control
• SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning
• Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping
• Sample-efficient Cross-Entropy Method for Real-time Planning
• Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Sampling
• Self-Supervised 3D Keypoint Learning for Ego-Motion Estimation
• Self-Supervised Learning of Scene-Graph Representations for Robotic Sequential Manipulation Planning
• Self-Supervised Object-in-Gripper Segmentation from Robotic Motions
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
• Sim-to-Real Transfer for Vision-and-Language Navigation
• Sim2Real Transfer for Deep Reinforcement Learning with Stochastic State Transition Delays
• SMARTS: An Open-Source Scalable Multi-Agent RL Training School for Autonomous Driving
• Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
• Soft Multicopter Control Using Neural Dynamics Identification
• SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
• Stein Variational Model Predictive Control
• STReSSD: Sim-To-Real from Sound for Stochastic Dynamics
• StrObe: Streaming Object Detection from LiDAR Packets
• Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering
• TartanVO: A Generalizable Learning-based VO
• Task-Relevant Adversarial Imitation Learning
• The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning
• The EMPATHIC Framework for Task Learning from Implicit Human Feedback
• The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation
• Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes
• TNT: Target-driveN Trajectory Prediction
• Tolerance-Guided Policy Learning for Adaptable and Transferrable Delicate Industrial Insertion
• Towards Autonomous Eye Surgery by Combining Deep Imitation Learning with Optimal Control
• Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
• Towards Robotic Assembly by Predicting Robust, Precise and Task-oriented Grasps
• Transformers for One-Shot Visual Imitation
• Transporter Networks: Rearranging the Visual World for Robotic Manipulation
• TriFinger: An Open-Source Robot for Learning Dexterity
• Uncertainty-Aware Constraint Learning for Adaptive Safe Motion Planning from Demonstrations
• Universal Embeddings for Spatio-Temporal Tagging of Self-Driving Logs
• Unsupervised Metric Relocalization Using Transform Consistency Loss
• Unsupervised Monocular Depth Learning in Dynamic Scenes
• Untangling Dense Knots by Learning Task-Relevant Keypoints
• Visual Imitation Made Easy
• Visual Localization and Mapping with Hybrid SFA
• Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter

---