Adaptive Motion Planning Framework Enhances Humanoid Robots' Ball Sports Performance
- Published
- Source
- IEEESpectrumAI
Humanoid robots are demonstrating improved capabilities in ball sports, yet replicating a professional athlete's motion style while ensuring reliable performance remains a challenge. This article discusses an adaptive motion planning and tracking framework that learns tennis serving and rally techniques from broadcast video and motion-capture data. The framework features a hierarchical design that separates the planner, responsible for generating stylistic kinematic motion, from the tracker, which executes the motion with minimal interference.
The significance of this framework lies in its ability to address the degradation of tracking performance when transitioning from simulation to physical hardware. By training the tracker on randomized execution speeds and conditioning the planner on a learned motion-speed representation, the framework minimizes errors caused by autoregressive planning and noisy perception. The research includes real-world validation on a humanoid platform and its application to a full-size humanoid robot, showcasing its ability to serve in uncontrolled environments without motion capture.
Looking ahead, the practical lessons derived from this research will be valuable for engineers developing future humanoid systems for ball sports. No further timeline was disclosed at the time of publication.
Original report
Learning to Play Like a Pro: Adaptive Motion Planning and Tracking for Humanoid Robots
IEEESpectrumAI · Noitom RoboticsThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
-
10
RobotToday Weekly October 5 – 9, 2026 RobotToday · 2 days ago
- 11
- 12
Related Suppliers
Noitom Robotics Technology (Shenzhen) Co., Ltd. 诺亦腾机器人
China
Shenzhen embodied-AI data company building motion-capture and teleoperation datasets for humanoid robots.
Tangible Robots
United States
San Francisco startup building Eggie, a wheeled humanoid with humanlike hands for household dexterity tasks, backed by Blume Ventures and Micelio.
Techsoft Robots 深圳市泰科智能机器人有限公司
China
Shenzhen manufacturer of humanoid and collaborative robot joint modules, servo drives, and dual-arm cobots for OEM and end-user customers.
AceiiLab 一思智能
China
AceiiLab is a Shenzhen-founded startup making the AceiiLab A1 AI tennis-serving robot with dual-lens vision, founded by ex-DJI and KUKA engineers.
Pong Robotics
United States
AI sports robotics brand by Shanghai Future Mind Co. (est. 2019) making AI-powered table tennis and tennis training robots sold in 80+ countries as PongBot.
Woan Technology (Shenzhen) Co., Ltd. 万安科技（深圳）有限公司
China
Shenzhen, China home-robotics company founded 2015, known internationally as SwitchBot; listed on the Hong Kong Stock Exchange in December 2025.
Tennibot
United States
Auburn, Alabama robotics company making autonomous tennis ball collecting and training robots, including the Rover collector and Partner ball machine.
Vsim
United Kingdom
Cambridge, UK firm incorporated 2022 by ex-Nvidia engineers; builds the Vlab GPU robot simulator and Vlearn framework, backed by a $21.5M seed.
Minerva Humanoids
United States
San Francisco startup founded 2025 by MIT, Tesla Optimus and Boston Dynamics alumni; builds the teleoperated humanoid Roger for oil, gas and EOD work.
Energid Technologies
United States
Advanced robotic motion control and machine vision software, acquired by Teradyne/Universal Robots.
CMES Robotics
United States
AI 3D robot-vision developer enabling robots to recognize irregular objects for depalletizing, picking and loading.
AMFITRACK™
Denmark
Danish 6DOF electromagnetic tracking system for robotics, VR/AR, simulation, and motion capture — no line-of-sight required.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
