CoRL 2023

193 papers

Top Research Directions

Research directions most represented by CoRL 2023 papers.

Bridging the Embodiment Gap in Robot Learning 9
Scaling Robotic Learning Beyond Expert Demonstrations 9
Safe Reinforcement Learning via Constrained Markov Decision Processes 8
Overcoming the Skill Library Bottleneck in Embodied Agents 7
Overcoming Visual Self Occlusion in Robotic Manipulation 7
Bridging the Exteroceptive Sensing Gap in Robotic Locomotion 6
Probabilistic Trajectory Forecasting for Autonomous Systems 6
Geometric Generalization in Robotic Manipulation 6
Scaling Robotic Control to High Dimensional Action Spaces 6
Generalizing Physical Dynamics Across Categories and Materials 5
Backpropagating Through Physical Laws for System Identification 5
Decoupling Semantic Planning from Sensorimotor Control 5
Fusing 2D Semantic Features with 3D Geometric Representations 5
Distribution Shift in Offline Reinforcement Learning 5
Cross-Embodiment Training for Generalist Robots 4

Top Authors

AuthorPapers
Chelsea Finn9
Dorsa Sadigh8
Fei Xia8
Sergey Levine8
Dieter Fox7
Jiajun Wu7
brian ichter6
Andy Zeng5
Danfei Xu5
Ken Goldberg5
Leslie Pack Kaelbling5
Raquel Urtasun5
Chen Wang4
Jie Tan4
Li Fei-Fei4
Pete Florence4
Quan Vuong4
Tomás Lozano-Pérez4
Wenhao Yu4
Abhishek Gupta3

Impactful Papers

Papers from CoRL 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
Learning to Drive Anywhere
Learning to See Physical Properties with Active Sensing Motor Policies
Leveraging 3D Reconstruction for Mechanical Search on Cluttered Shelves
M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place
ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting
Marginalized Importance Sampling for Off-Environment Policy Evaluation
Measuring Interpretability of Neural Policies of Robots with Disentangled Representation
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors
Multi-Resolution Sensing for Real-Time Control with Vision-Language Models
Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning
Neural Field Dynamics Model for Granular Object Piles Manipulation
Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control
NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities
One-Shot Imitation Learning: A Pose Estimation Perspective
One-shot Imitation Learning via Interaction Warping
Online Learning for Obstacle Avoidance
Online Model Adaptation with Feedforward Compensation
On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation Skills
Open-World Object Manipulation using Pre-Trained Vision-Language Models
OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data
PairwiseNet: Pairwise Collision Distance Learning for High-dof Robot Systems
Parting with Misconceptions about Learning-based Vehicle Motion Planning
PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play
PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining
PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
Policy Stitching: Learning Transferable Robot Policies
Polybot: Training One Policy Across Robots While Embracing Variability
Precise Robotic Needle-Threading with Tactile Perception and Reinforcement Learning
PreCo: Enhancing Generalization in Co-Design of Modular Soft Robots via Brain-Body Pre-Training
Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks
Predicting Routine Object Usage for Proactive Robot Assistance
Preference learning for guiding the tree search in continuous POMDPs
Push Past Green: Learning to Look Behind Plant Foliage by Moving It
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier
Ready, Set, Plan! Planning to Goal Sets Using Generalized Bayesian Inference
Rearrangement Planning for General Part Assembly
REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation
Reinforcement Learning Enables Real-Time Planning and Control of Agile Maneuvers for Soft Robot Arms
Revisiting Depth-guided Methods for Monocular 3D Object Detection by Hierarchical Balanced Depth
RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot
RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools
RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning
Robot Learning with Sensorimotor Pre-training
Robot Parkour Learning
Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

« prev Page 3/4 next »