Researcher Masayoshi Tomizuka

Researcher Biography
http://www.me.berkeley.edu/people/faculty/masayoshi-tomizuka

Current Projects

Automatic Semantics Extraction and Representation for High-Definition Map Construction and Scene Understanding
Deep Learning-Based Vehicle Control Strategist for Autonomous Vehicles
Efficient Model for Large-Scale Point Cloud Perception
Embracing Uncertainties in 3D Object Detection -- from Annotation and Benchmarking to Failure Analysis and Data Augmentation

Past Projects

3D Object Detection based on Lidar and Camera Fusion
Data Augmentation via Synthetic Point Cloud for 3D Detection Refinement and Domain Adaptation with Different LiDAR Configurations
Fast Inverse Vehicle Dynamics Adaptation for Driving Policy Transfer via Meta Learning
Generic Motion Generation and Comprehension with Social Interactions
Interpretable and Data-Efficient Driving Behavior Generation via Deep Generative Probabilistic and Logic Models
Localization and 3D Detection via Fusing Sparse Point Cloud and Information from Visual-Inertial Navigation System
Motion Prediction for Urban Autonomous Driving Based on Stochastic Policy Learned via Deep Neural Network
Time-Series LIDAR and Camera Fusion with Structured Variational Inference