Robot

Engineering

Object detection

Computer security

Systems engineering

Computer science

Grid

Geology

Task (project management)

Point cloud

Pattern recognition (psychology)

Mathematics

Politics

Political science

Object (grammar)

Mobile robot

Occupancy grid mapping

Artificial intelligence

Geometry

Remote sensing

Representation (politics)

Deep learning

Lidar

Artificial neural network

Cognitive neuroscience of visual object recognition

Convolutional neural network

Computer vision

Key (lock)

Robust object recognition is a crucial skill for robots operating autonomously in real world environments. Range sensors such as LiDAR and RGBD cameras are increasingly found in modern robotic systems, providing a rich source of 3D information that can aid in this task. However, many current systems do not fully utilize this information and have trouble efficiently dealing with large amounts of point cloud data. In this paper, we propose VoxNet, an architecture to tackle this problem by integrating a volumetric Occupancy Grid representation with a supervised 3D Convolutional Neural Network (3D CNN). We evaluate our approach on publicly available benchmarks using LiDAR, RGBD, and CAD data. VoxNet achieves accuracy beyond the state of the art while labeling hundreds of instances per second.

VoxNet: A 3D Convolutional Neural Network for real-time object recognition