Robotics, autonomy & AI

Karl Berntorp

I lead robotics, autonomy, and AI development, combining technical strategy and team leadership with hands-on work that turns research into practical systems.

publications
Approximately 130
granted US patents
Approximately 50

Selected impact

Experience

Chewy

July 2025–present

Principal Research Scientist

  • Lead autonomy algorithm strategy and cross-functional development for mobile manipulation systems, from research through validation and engineering handoff.
  • Built and physically validated a robot-management system using an AI-assisted code-factory workflow, integrating mapping, scene understanding, task allocation, and routing.
  • Lead work on reliable robotic manipulation of heavy, deformable items.

Walmart Advanced Systems & Robotics / Symbotic

2024–2025

Algorithms leadership and Distinguished Scientist roles

Joined Symbotic following its acquisition of WASR.

  • Led task allocation, routing, resource allocation, and control for autonomous robot fleets at WASR, followed by cross-functional algorithm leadership at Symbotic.
  • Developed research teams through goal setting and mentoring, and partnered with software engineers to move algorithms into production.
  • At WASR, proposed and prototyped routing improvements and worked with software engineers to deploy them, achieving 10% higher pick rates and a 30% reduction in long-tail dispense and product task times in production.
  • Named inventor on a Symbotic patent application for coordinating multiple robots.

Mitsubishi Electric Research Laboratories

2014–2017; 2019–October 2024

Roles included Control for Autonomy Team Leader and Senior Principal Researcher.

  • Managed a research team and led multi-group programs, setting technical direction and mentoring researchers across autonomy, positioning, and perception and control.
  • Co-designed and launched MERL’s inaugural postdoctoral program with its CEO and VP.
  • Designed, analyzed, and implemented in C a satellite-positioning estimation algorithm that demonstrated less than 3 cm positioning error over 24 hours in experiments on customer data.

Education and service: PhD in Automatic Control, Lund University. IEEE Senior Member, with editorial service for IEEE Transactions on Control Systems Technology.

Entrepreneurship: Founder of AB Berntec and co-founder of AB Benoso, engineering consultancies serving industrial clients.

Selected research

All publications

2020 Vehicle System Dynamics

Trajectory Tracking for Autonomous Vehicles on Varying Road Surfaces by Friction-Adaptive Nonlinear Model Predictive Control

Develops friction-adaptive nonlinear model predictive control for trajectory tracking on changing road surfaces.

Connect

Working across research and practice.

Interested in discussing robotics, autonomy, AI, or technical leadership? Get in touch.

Get in touch