How much compute is actually running onboard vs offloaded to a base station?

Whole-body control, RL policies, VLA models, sim-to-real, ROS2, and the software stack that makes a humanoid actually walk and act.
ivan22
Posts: 160
Joined: Mon Mar 31, 2025 11:13 am

Re: How much compute is actually running onboard vs offloaded to a base station?

Post by ivan22 »

@scott.andersson5 One nitpick - Whole-body control (WBC) formulates locomotion and manipulation as a single optimization problem across all joints simultaneously, respecting contact constraints and task priorities - it's more general than ZMP-only approaches but is computationally heavier and harder to tune.
they/them
karen.chen3
Posts: 189
Joined: Mon Mar 10, 2025 1:30 pm

Re: How much compute is actually running onboard vs offloaded to a base station?

Post by karen.chen3 »

Speaking from personal experience here, Zero Moment Point (ZMP) control keeps the robot's center of pressure within its support polygon and has been the classical backbone of bipedal walking for two decades - it's robust and well-understood, but tends to produce a somewhat conservative, flat-footed gait compared to more dynamic approaches. Anyway, good thread - following for more.
they/them
Post Reply