CoRL 2022

195 papers

Top Research Directions

Research directions most represented by CoRL 2022 papers.

Zero-Shot Sim-to-Real Transfer for Robotic Control 16
Overcoming Visual Self Occlusion in Robotic Manipulation 11
Bridging the Embodiment Gap in Robot Learning 9
Scaling Robotic Control to Long-Horizon Multi-Stage Tasks 8
Scaling Robotic Control to High Dimensional Action Spaces 8
Overcoming Depth Sensor Failures on Transparent Surfaces 7
Scaling Robotic Learning Beyond Expert Demonstrations 7
Sample Efficient Reinforcement Learning 7
The Reward Engineering Bottleneck in Reinforcement Learning 6
Optimization through Discontinuous Contact Dynamics 5
Overcoming Sensor Occlusion Through Collaborative Perception 5
Model Free Generalizable 6D Object Pose Estimation 5
Safe Reinforcement Learning via Constrained Markov Decision Processes 5
Sensor Noise Robustness for Sim-to-Real Transfer 5
Inferring Latent Physical Properties from Object Interactions 4

Top Authors

AuthorPapers
Sergey Levine7
Dieter Fox6
David Held5
Dorsa Sadigh5
Pieter Abbeel5
Andy Zeng4
Deepak Pathak4
Fei Xia4
Adrien Gaidon3
Akshara Rai3
Alberto Rodriguez Garcia3
brian ichter3
Byron Boots3
Chelsea Finn3
Jiajun Wu3
Jitendra Malik3
Karol Hausman3
Ken Goldberg3
Li Fei-Fei3
Marco Pavone3

Impactful Papers

Papers from CoRL 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Safe Robot Learning in Assistive Devices through Neural Network Repair
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer
SE(2)-Equivariant Pushing Dynamics Models for Tabletop Object Manipulations
SE(3)-Equivariant Point Cloud-Based Place Recognition
SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation
Selective Object Rearrangement in Clutter
Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models
Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning
Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data
Skill-based Model-based Reinforcement Learning
Socially-Attentive Policy Optimization in Multi-Agent Self-Driving System
Solving Complex Manipulation Tasks with Model-Assisted Model-Free Reinforcement Learning
SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
Synthesizing Adversarial Visual Scenarios for Model-Based Robotic Control
Tailoring Visual Object Representations to Human Requirements: A Case Study with a Recycling Robot
Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles
TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds
Topological Semantic Graph Memory for Image-Goal Navigation
Touching a NeRF: Leveraging Neural Radiance Fields for Tactile Sensory Data Generation
Towards Capturing the Temporal Dynamics for Trajectory Prediction: a Coarse-to-Fine Approach
Towards Long-Tailed 3D Detection
Towards Online 3D Bin Packing: Learning Synergies between Packing and Unpacking via DRL
Towards Scale Balanced 6-DoF Grasp Detection in Cluttered Scenes
TrackletMapper: Ground Surface Segmentation and Mapping from Traffic Participant Trajectories
Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning
Transferring Hierarchical Structures with Dual Meta Imitation Learning
Transformers Are Adaptable Task Planners
TRITON: Neural Neural Textures for Better Sim2Real
USHER: Unbiased Sampling for Hindsight Experience Replay
Verified Path Following Using Neural Control Lyapunov Functions
VideoDex: Learning Dexterity from Internet Videos
VIOLA: Object-Centric Imitation Learning for Vision-Based Robot Manipulation
VIRDO++: Real-World, Visuo-tactile Dynamics and Perception of Deformable Objects
Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation
Visuotactile Affordances for Cloth Manipulation with Local Control
Visuo-Tactile Transformers for Manipulation
Volumetric-based Contact Point Detection for 7-DoF Grasping
Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation
Where To Start? Transferring Simple Skills to Complex Environments
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example

« prev Page 4/4