Skip to main content Link Search Menu Expand Document (external link)

Deep Learning Research Papers for Robot Perception, Grasping and Manipulation

A collection of deep learning research papers with coverage in perception and associated robotic tasks. Within each research area outlined below, the course staff has identified a core and extended set of research papers. The core set of papers will form the basis of our seminar-style lectures starting in week 7. The extended set provides additional coverage of even more exciting work being done within each area.

Table of contents

  1. RGB-D Architectures
    1. Core List
    2. Extended List
  2. Pointcloud Processing
    1. Core List
    2. Extended List
  3. Object Pose, Geometry, SDF, Implicit surfaces
    1. Core List
    2. Extended List
  4. Dense object descriptors, Category-level representations
    1. Core List
    2. Extended List
  5. Recurrent Networks and Object Tracking
    1. Core List
    2. Extended List
  6. Visual Odometry and Localization
    1. Core List
    2. Extended List
  7. Semantic Scene Graphs and Explicit Representations
    1. Core List
    2. Extended List
  8. Neural Radiance Fields and Implicit Representations
    1. Core List
    2. Extended List
  9. Datasets
  10. Self-Supervised Learning
    1. Core List
  11. Grasp Pose Detection
    1. Core List
    2. Extended List
  12. Tactile Perception for Grasping and Manipulation
    1. Core List
    2. Extended List
  13. Pre-training for Robot Manipulation and Transformer Architectures
    1. Core List
    2. Extended List
  14. More Frontiers
    1. Interpreting Deep Learning Models
    2. Fairness and Ethics
    3. Articulated and Deformable Objects
    4. Transparent Objects
    5. Dynamic Scenes

RGB-D Architectures

Core List

Extended List

Pointcloud Processing

Core List

Extended List

Object Pose, Geometry, SDF, Implicit surfaces

Core List

Extended List

Dense object descriptors, Category-level representations

Core List

Extended List

Recurrent Networks and Object Tracking

Core List

Extended List

Visual Odometry and Localization

Core List

Extended List

Semantic Scene Graphs and Explicit Representations

Core List

Extended List

Neural Radiance Fields and Implicit Representations

Core List

Extended List

Datasets

RGB-D Datasets:

Collecting data with robots:

Semantic Datasets:

Object Model Datasets:

Simulators:

Self-Supervised Learning

Core List

Grasp Pose Detection

Core List

Extended List

Tactile Perception for Grasping and Manipulation

Core List

Extended List

Pre-training for Robot Manipulation and Transformer Architectures

Core List

Extended List

More Frontiers

Interpreting Deep Learning Models

Fairness and Ethics

Articulated and Deformable Objects

Transparent Objects

Dynamic Scenes


Institutional Teaching Collaborative