The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Humanoids
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Business
    • Financial
      • Investments
      • Mergers & Acquisitions
      • Earnings
    • Markets
      • Agriculture
      • Healthcare
      • Logistics
      • Manufacturing
      • Mining
      • Security
    • RBR50
      • RBR50 Winners 2025
      • RBR50 Winners 2024
      • RBR50 Winners 2023
      • RBR50 Winners 2022
      • RBR50 Winners 2021
  • Resources
    • Automated Warehouse Research Reports
    • Digital Issues
    • eBooks
    • Publications
      • Automated Warehouse
      • Collaborative Robotics Trends
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
  • Advertise
  • Subscribe

Bedrock Robotics announces autonomous excavation milestone

By Mike Oitzman | November 20, 2025

a caterpillar excavator autonomously loads dirt into a dump truck.

Large excavators are autonomously removing dirt on construction sites. | Credit: Bedrock Robotics

Bedrock Robotics LLC, which has developed autonomy for excavators, demonstrated the capabilities of its technology with partner Sundt Construction Inc. on the set preparation of a 130-acre (52.6 ha) manufacturing facility.

On this project alone, Bedrock’s systems have so far moved over 65,000 cubic yards (49, 696 cubic m) by loading human-operated, articulating dump trucks using the same workflow employed in manual operations. This integration represents a leap forward in commercial autonomous construction, said the companies.

“The biggest challenge we face isn’t just finding operators; it’s keeping experienced ones engaged when we need them for months of repetitive earthmoving in remote locations,” said Dan Green, project manager at Sundt Construction.

“Our best operators aren’t interested in the monotony of mass excavation work,” he added. “With Bedrock’s technology handling the repetitive truck loading that goes on day after day, our skilled workforce can focus on more specialized and creative problems where their expertise is critical to success.”

Bedrock Robotics rapidly iterates for Operator AI

Bedrock Robotics’ core technology is the Bedrock Operator, an AI controller trained to operate the excavator. The San Francisco company has also integrated it with excavator models ranging from 20-ton to 80-ton machines, across a number of the leading heavy equipment manufacturers.

Since its founding in 2024, Bedrock has rapidly iterated on its product. The company went from initial simulation to integrating its first machine (named “Fred”) in just four to five months. By November 2024, Bedrock was testing autonomy on a real site, and it continuously improved its models by collecting real-world data.

The leadership team at Bedrock includes several alumni of autonomous vehicle developer Waymo. Co-founder and CEO Boris Sofman led autonomous trucking and core technologies for Waymo’s public robotaxi network. Other Bedrock co-founders include Kevin Peterson, Ajay Gummalla, and Matthieu Guilbert, all of whom were with Sofman at Waymo.

Sofman told The Robot Report that “a key part of [the development at Bedrock] was a really aggressive shift from the traditional robotics approaches of search and heuristics and these engineered solutions to aggressively embracing machine learning and data-driven approaches to basically capture from math scale data how you solve this infinitely complex problem.”

How did Bedrock develop its product and pivot so quickly?

“We did not have engineers writing software to explain how to operate this machine,” Sofman explained. “We have huge amounts of data, and we have engineers thinking about how to manipulate the data sets and the cost functions and evaluation schemes, and how to structure the problem and manage these large-scale models.”

The evolution of large language models (LLMs) parallels the development of artificial intelligence for robotics, noted Sofman.

“In the same way that an LLM spits out tokens of words … we’re spitting out a trajectory for a high-dimensional machine and body,” he said. “We’re effectively learning from how to emulate the best operators.”

close up look at the set of camera and sensors installed above the cab of the excavator. Bedrock Robotics has designed autonomy systems for construction.

Sensors are mounted above the driver’s cab to provide visibility to the excavator’s work envelope. | Credit: Bedrock Robotics

Partnerships keep safety paramount

Safety remains essential to the deployment of robotics for the real world, especially with large industrial equipment like excavators. In order to better understand the construction market, Bedrock has continued to expand its network of industry collaborators, welcoming Austin Bridge & Road, Maverick Constructors, and Haydon Companies.

These companies join an existing ecosystem that includes Zachry Construction, Sundt Construction, Champion Site Prep, and Capitol Aggregates. Bedrock said its partners help to accelerate the adoption of autonomy across commercial, industrial, and heavy civil applications while ensuring the technology is developed with visibility into the full spectrum of construction scenarios that contractors face daily.

“Safety is at the heart of all we do, and technology has the potential to further enhance the safe performance of work at our job sites,” said Bill Heathcott, executive vice president at Austin Bridge & Road. “Our partnership with Bedrock Robotics has opened the door to autonomous equipment, a game-changer in next-level worker protection, as well as increased efficiency and precision. Together, we’re exploring how this innovation could change construction for the better, help to solve critical skilled-labor shortages, and ultimately allow our crews to get more done.”

About The Author

Mike Oitzman

Mike Oitzman is Senior Editor of WTWH's Robotics Group and founder of the Mobile Robot Guide. Oitzman is a robotics industry veteran with 25-plus years of experience at various high-tech companies in the roles of marketing, sales and product management. Mike has a BS in Systems Engineering from UCSD and an MBA from Golden Gate University. He can be reached at [email protected].

Comments

  1. Jamesschwartz says

    November 21, 2025 at 5:45 pm

    I think it’s a bunch of horse shit that there isn’t enough people to run these machines. Operating engineers are some of the best compensated in the construction industry. This is about profits and profits alone. Once you phase out construction workers what will the economy look like then?

    Reply

Tell Us What You Think! Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles Read More >

profile view of the maximo solar installation robot.
Transforming solar farms: AI, robotics, and industry partnerships at AES
closeup of the LCM chip.
Programmable optics pioneer Lumotive opens new centers in Oman and Taiwan
Antioch co-founders Harry Mellsop, Alex Langshur, Colton Swingle, and Collin Schlager.
Antioch raises pre-seed funding to accelerate AI robotics testing
CivNav works with existing solar equipment such as this loader, says Civ Robotics.
Civ Robotics provides CivNav AI navigation for solar construction systems

RBR50 Innovation Awards

“rr
EXPAND YOUR KNOWLEDGE AND STAY CONNECTED
Get the latest info on technologies, tools and strategies for Robotics Professionals.

Latest Episode of The Robot Report Podcast

Automated Warehouse Research Reports

Sponsored Content

  • Supporting the future of medical robotics with smarter motor solutions
  • YUAN Unveils Next-Gen AI Robotics Powered by NVIDIA for Land, Sea & Air
  • ASMPT chooses Renishaw for high-quality motion control
  • Revolutionizing Manufacturing with Smart Factories
  • How to Set Up a Planetary Gear Motion with SOLIDWORKS
The Robot Report
  • Automated Warehouse
  • RoboBusiness Event
  • Robotics Summit & Expo
  • About The Robot Report
  • Subscribe
  • Contact Us

Copyright © 2025 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Humanoids
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Business
    • Financial
      • Investments
      • Mergers & Acquisitions
      • Earnings
    • Markets
      • Agriculture
      • Healthcare
      • Logistics
      • Manufacturing
      • Mining
      • Security
    • RBR50
      • RBR50 Winners 2025
      • RBR50 Winners 2024
      • RBR50 Winners 2023
      • RBR50 Winners 2022
      • RBR50 Winners 2021
  • Resources
    • Automated Warehouse Research Reports
    • Digital Issues
    • eBooks
    • Publications
      • Automated Warehouse
      • Collaborative Robotics Trends
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
  • Advertise
  • Subscribe