Robotics is advancing quickly, but building systems that can operate reliably in the real world remains one of the most complex challenges in technology.

In this episode of Automated, Brian Heater speaks with Zachary Jackowski of Boston Dynamics about the shift from research to commercialization and why generalization is emerging as the defining problem in modern robotics.

Zachary explains how Boston Dynamics approaches robot design, from early research platforms like Atlas R1 to more refined production systems. Early versions prioritize exploration and performance, while newer iterations focus on reliability, repairability, and deployment in real environments. This evolution reflects a broader shift across the industry toward building systems that can move beyond controlled demos and operate consistently in the field.

The conversation explores why generalization is critical for robotics. Training robots on a single task does not prepare them for real-world variability. Instead, diverse data, multiple environments, and exposure to different behaviors are required to build systems that can adapt and perform across use cases.

They also discuss the challenge of data collection and deployment, including the chicken-and-egg problem of needing real-world data to improve systems that are not yet ready for large-scale deployment. Incremental rollout, focused applications, and controlled environments are key steps in bridging that gap.

The episode also examines why industrial environments are the starting point for humanoid robots. Factories provide structure, repeatability, and trained operators, while home environments introduce unpredictability that current systems are not yet equipped to handle at scale.

Brian and Zachary also explore how different robot platforms, including humanoids, quadrupeds, and wheeled systems, each serve distinct roles. Rather than a single dominant design, the future of robotics will likely involve multiple systems working together and benefiting from shared data and learning.

From actuator design and system simplification to deployment strategy and data diversity, this conversation offers a grounded look at what it takes to bring robotics into real-world applications.

KEY MOMENTS

(00:00) Boston Dynamics and the shift to commercialization

(02:11) Zachary’s path into robotics and Boston Dynamics

(04:16) From research to product development

(07:19) Research versus commercialization in robotics

(08:53) Why early robots are built differently

(11:16) Designing better systems through iteration

(13:22) Advances in actuator performance

(14:36) Safety and robot design decisions

(16:11) Why humanoid robots are just the starting point

(17:21) Why generalization is the real breakthrough

(20:10) The data collection challenge in robotics

(21:31) Why data diversity matters more than volume

(23:24) Why robots are going to factories first

25:52 Why robots are not ready for homes

31:34 Why complexity increases in real-world robotics

We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org.

You can find the transcript and more episodes of Automated at automated.fm.

Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify.

Subscribe to the Automated Newsletter:

https://www.automate.org/automation/newsletter-automation-roundup

You can also find us on:

LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/

Instagram https://www.instagram.com/automatedpod/

Hosted on Acast. See acast.com/privacy for more information.

Zachary Jackowski on Generalization in Robotics and the Reality of Deploying Robots in the Real World

Automated with Brian Heater

Zachary Jackowski on Generalization in Robotics and the Reality of Deploying Robots in the Real World