Sotabase

Career

· Co-Founder, CTO, Ambi Robotics2021–
· Co-Founder, CEO, Ambi Robotics2019–2021
· Postdoctoral Scholar, University of California, Berkeley2018–2019
· Computer Vision Engineer, Occipital2015–2016
· Graduate Student Researcher, UC Berkeley Electrical Engineering & Computer Sciences (EECS)2013–2018
· Co-Founder, Computer Vision Engineer, Lynx Laboratories2012–2015
· Student Technician, Applied Research Labs2011–2012
· Software Engineering Intern, Google2011–2011
· PhD, University of California Berkeley2011–2018
· B.S., The University of Texas at Austin2009–2013

Publications (46)

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
Robotics: Science and Systems · 2017
1,348
cited
Learning ambidextrous robot grasping policies
Science Robotics · 2019
567
cited
Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a Multi-Armed Bandit model with correlated rewards
IEEE International Conference on Robotics and Automation · 2016
374
cited
Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning
IEEE International Conference on Robotics and Automation · 2018
226
cited
Learning Deep Policies for Robot Bin Picking by Simulating Robust Grasping Sequences
Conference on Robot Learning · 2017
199
cited
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
IEEE International Conference on Robotics and Automation · 2018
189
cited
Dex-Net 3.0: Computing Robust Robot Suction Grasp Targets in Point Clouds using a New Analytic Model and Deep Learning
arXiv.org · 2017
134
cited
Autonomous multilateral debridement with the Raven surgical robot
IEEE International Conference on Robotics and Automation · 2014
133
cited
On-Policy Dataset Synthesis for Learning Robot Grasping Policies Using Fully Convolutional Deep Networks
IEEE Robotics and Automation Letters · 2019
114
cited
Learning accurate kinematic control of cable-driven surgical robots using data cleaning and Gaussian Process Regression
2014 IEEE International Conference on Automation Science and Engineering (CASE) · 2014
83
cited
Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations
IEEE International Conference on Robotics and Automation · 2016
78
cited
SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces
IEEE International Conference on Robotics and Automation · 2016
72
cited
GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming
IEEE International Conference on Robotics and Automation · 2015
70
cited
Linear Push Policies to Increase Grasp Access for Robot Bin Picking
2018 IEEE 14th International Conference on Automation Science and Engineering (CASE) · 2018
58
cited
Design of parallel-jaw gripper tip surfaces for robust grasping
IEEE International Conference on Robotics and Automation · 2017
48
cited
Energy-Bounded Caging: Formal Definition and 2-D Energy Lower Bound Algorithm Based on Weighted Alpha Shapes
IEEE Robotics and Automation Letters · 2016
44
cited
Multi-armed bandit models for 2D grasp planning with uncertainty
2015 IEEE International Conference on Automation Science and Engineering (CASE) · 2015
42
cited
Adversarial Grasp Objects
2019 IEEE 15th International Conference on Automation Science and Engineering (CASE) · 2019
38
cited
A cloud robot system using the dexterity network and berkeley robotics and automation as a service (Brass)
IEEE International Conference on Robotics and Automation · 2017
35
cited
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds
arXiv.org · 2018
32
cited
Sotabase
Jeff Mahler | Researcher Profile | Sotabase | Sotabase