AthenaZero: A low-inertia, bimanual robot for dynamic manipulation

📅 2026-09-15
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
AthenaZero通过使用准直驱和远程传动技术减少惯性,实现动态操控,如投掷、接球和击打任务。
📝 Abstract
AthenaZero is a bimanual manipulator designed to minimize inertia without compromising control authority. By utilizing quasi-direct drive actuation and transmission remotization techniques, the system achieves an effective endpoint mass comparable to that of a human---about an order of magnitude less than conventional robot manipulators. This characteristic, combined with its inherent torque transparency, makes AthenaZero exceptionally well-suited for dynamic manipulation. We describe the methodology} that led to this design and demonstrate the robot's capabilities on three baseball-inspired tasks: throwing, catching, and batting, which showcase complex interactions on human-comparable timescales where milliseconds matter. AthenaZero was capable of throwing at speeds in excess of 30 m/s, with catching and batting at speeds in excess of 14 m/s over a short 7.3 m distance. Batting practice and a game of catch were subsequently performed in robot-to-robot and human-to-robot variations, showcasing the efficacy and adaptability of our system in tasks that require high acceleration.
Problem

Research questions and friction points this paper is trying to address.

low-inertia
bimanual robot
dynamic manipulation
quasi-direct drive actuation
transmission remotization
Innovation

Methods, ideas, or system contributions that make the work stand out.

quasi-direct drive actuation
transmission remotization
low-inertia
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Andrew S. Morgan
Andrew S. Morgan
Robotics and AI Institute (RAI)
Robot ManipulationMotion PlanningControl
G
Gregory Xie
RAI Institute, Cambridge, Massachusetts, 02142, USA
C
Capprin Bass
RAI Institute, Cambridge, Massachusetts, 02142, USA
R
Rachel Thomasson
RAI Institute, Cambridge, Massachusetts, 02142, USA
C
Chunpeng Wang
RAI Institute, Cambridge, Massachusetts, 02142, USA
E
Erfan Shahriari
RAI Institute, Cambridge, Massachusetts, 02142, USA
H
Harrison Busa
RAI Institute, Cambridge, Massachusetts, 02142, USA
O
Oluwaseun Araromi
RAI Institute, Cambridge, Massachusetts, 02142, USA
J
Joseph Aronov
RAI Institute, Cambridge, Massachusetts, 02142, USA
Michael Burgess
Michael Burgess
Massachusetts Institute of Technology
Robotic manipulation
V
Velin D. Dimitrov
RAI Institute, Cambridge, Massachusetts, 02142, USA
M
Matthew A. Estrada
RAI Institute, Cambridge, Massachusetts, 02142, USA
F
Faris Hamdi
RAI Institute, Cambridge, Massachusetts, 02142, USA
S
Samuel Kendig
RAI Institute, Cambridge, Massachusetts, 02142, USA
Taeyoon Lee
Taeyoon Lee
Professor of Electrical and Electronic Engineering, Yonsei University
Fiber electronicsTextile electronicsWearable electronicsBiomaterialsSemiconducting materials
J
Jose Oscar Mur-Miranda
RAI Institute, Cambridge, Massachusetts, 02142, USA
E
Emma Sommers
RAI Institute, Cambridge, Massachusetts, 02142, USA
P
Paul Titchener
RAI Institute, Cambridge, Massachusetts, 02142, USA
M
Margaret Wang
RAI Institute, Cambridge, Massachusetts, 02142, USA
Achu Wilson
Achu Wilson
Boston Dynamics Robotics & AI Institute, Cambridge, MA, USA
Roboticsmanipulationtactile sensinggraspingReinforcement Learning
Mark Yeatman
Mark Yeatman
RAI Institute, Cambridge, Massachusetts, 02142, USA
O
Osman Dogan Yirmibesoglu
RAI Institute, Cambridge, Massachusetts, 02142, USA
Alfred A. Rizzi
Alfred A. Rizzi
RAI Institute, Cambridge, Massachusetts, 02142, USA
A
Annan Mozeika
RAI Institute, Cambridge, Massachusetts, 02142, USA
Nicolas Rojas
Nicolas Rojas
RAI Institute, Cambridge, Massachusetts, 02142, USA