CoRL 2021

169 papers

Top Research Directions

Research directions most represented by CoRL 2021 papers.

Safe Reinforcement Learning via Constrained Markov Decision Processes 13
Sample Efficient Reinforcement Learning 8
Zero-Shot Sim-to-Real Transfer for Robotic Control 8
Scaling Robotic Control to Long-Horizon Multi-Stage Tasks 6
Beyond Planar Constraints in Robotic Manipulation 5
Privileged Information Distillation for Sim-to-Real Policy Transfer 5
Bridging the Embodiment Gap in Robot Learning 5
Modeling Reciprocal Dynamics in Multi-Agent Trajectory Prediction 5
Mitigating Cumulative Error in Odometry and Mapping Systems 5
Scaling Robotic Learning Beyond Expert Demonstrations 5
Reset-Free Reinforcement Learning 4
Grounding High Level Reasoning in Low Level Motor Control 4
The Reward Engineering Bottleneck in Reinforcement Learning 4
Mitigating Compounding Errors in Behavioral Cloning 4
Mitigating Compounding Errors in Imitation Learning 4

Top Authors

AuthorPapers
Dieter Fox9
Sergey Levine8
Li Fei-Fei7
Silvio Savarese6
Chelsea Finn5
Dorsa Sadigh5
Jiajun Wu5
Byron Boots4
Chris Paxton4
Edward Johns4
Jeannette Bohg4
Martin Riedmiller4
Pulkit Agrawal4
Roberto Martín-Martín4
Abhinav Gupta3
Ajay Mandlekar3
Animesh Garg3
Arsalan Mousavian3
Corey Lynch3
Daniela Rus3

Impactful Papers

Papers from CoRL 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Model-free Safe Control for Zero-Violation Reinforcement Learning
Motion Forecasting with Unlikelihood Training in Continuous Space
Motivating Physical Activity via Competitive Human-Robot Interaction
MuGNet: Multi-Resolution Graph Neural Network for Segmenting Large-Scale Pointclouds
Multi-Agent Trajectory Prediction by Combining Egocentric and Allocentric Views
Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
My House, My Rules: Learning Tidying Preferences with Graph Neural Networks
Neural Posterior Domain Randomization
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning
ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
Orientation Probabilistic Movement Primitives on Riemannian Manifolds
Parallelised Diffeomorphic Sampling-based Motion Planning
Predicting Stable Configurations for Semantic Placement of Novel Objects
Probabilistic and Geometric Depth: Detecting Objects in Perspective
Rapid Exploration for Open-World Navigation with Latent Goal Models
Redundancy Resolution as Action Bias in Policy Search for Robotic Manipulation
ReSkin: versatile, replaceable, lasting tactile skins
RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks
Risk-Averse Zero-Order Trajectory Optimization
RoboFlow: a Data-centric Workflow Management System for Developing AI-enhanced Robots
Robot Reinforcement Learning on the Constraint Manifold
Robots on Demand: A Democratized Robotics Research Cloud
RoCUS: Robot Controller Understanding via Sampling
Rough Terrain Navigation Using Divergence Constrained Model-Based Reinforcement Learning
S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics
Safe Driving via Expert Guided Policy Optimization
Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions
Scaling Up Multi-Task Robotic Reinforcement Learning
SCAPE: Learning Stiffness Control from Augmented Position Control Experiences
Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects
Self-Improving Semantic Perception for Indoor Localisation
Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
Semantic Terrain Classification for Off-Road Autonomous Driving
SeqMatchNet: Contrastive Learning with Sequence Matching for Place Recognition & Relocalization
SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo
Single-Shot Scene Reconstruction
Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback
Smooth Exploration for Robotic Reinforcement Learning
Social Interactions as Recursive MDPs
SORNet: Spatial Object-Centric Representations for Sequential Manipulation
Specializing Versatile Skill Libraries using Local Mixture of Experts
Stochastic Policy Optimization with Heuristic Information for Robot Learning
STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
Strength Through Diversity: Robust Behavior Learning via Mixture Policies
Structured deep generative models for sampling on constraint manifolds in sequential manipulation
Structure from Silence: Learning Scene Structure from Ambient Sound
Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear
Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation

« prev Page 3/4 next »