Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Outplaying Elite Table Tennis Players with an Autonomous Robot

Outplaying Elite Table Tennis Players with an Autonomous Robot.
Peter Duerr, Mireille El Gheche, Guilherme Jorge Maeda, Nobuhiko Mukai, Naoya Takahashi, Stefan Heusser, Hamdi Sahloul, Yamen Saraiji, Pavel Adodin, Yin Bi, Sam Blakeman, Christian Conti, Dunai Fuentes Hitos, Yunpu Hu, Farshad Khadivar, Raphaela Kreiser, Luz Martinez, Fabian Schilling, Ricardo Tapiador Morales, Guillem Torrente, Mario Ynocente Castro, Lison Abecassis, Alberto Giammarino, Yu-Ting Huang, Yannik Nagel, Andrea Scotti, Alexander Sigrist, Tiago Silva, Etienne Walther, Jengyan Wong, Bilan Yang, Asude Aydin, Divij Grover, Apurv Saha, Valentina Cavinato, Takekazu Kakinuma, Taishi Kunori, Valentin Monferrato, Stefan Richter, Stefanos Charalambous, Simon Guist, MadsAlber Kuhlmann-Jorgensen, Lorenzo Miele, Agis Politis, Mattia Scardecchia, Hiroaki Kitano, Peter R. Wurman, Peter Stone, and Michael Spranger.
Nature, 2026.
The official paper from Nature
The supplementary material
A video about the project
The project website

Download

(unavailable)

Abstract

Artificial intelligence (AI) systems now challenge or surpass human experts in many computer games1,2. Physical and real-time sports such as table tennis, however, remain a major open challenge because of their requirements for fast, precise and adversarial interactions near obstacles and at the edge of human reaction time3. Here we present Ace, to our knowledge the first real-world autonomous system competitive with elite human table tennis players. Ace addresses the challenges of physical real-time interaction through a new, high-speed perception system using event-based vision sensors4, and a new control system based on model-free reinforcement learning, as well as state-of-the-art high-speed robot hardware. Evaluated in matches against elite and professional players under official competition rules, Ace achieved several victories and demonstrated consistent returns of high-speed, high-spin shots. These results highlight the potential of physical AI agents to perform complex, real-time interactive tasks, suggesting broader applications in domains requiring fast, precise human-robot interaction.

BibTeX Entry

@Article{peter_nature_2026,
  author   = {Peter Duerr and Mireille El Gheche and Guilherme Jorge Maeda and Nobuhiko Mukai and Naoya Takahashi and Stefan Heusser and Hamdi Sahloul and Yamen Saraiji and Pavel Adodin and Yin Bi and Sam Blakeman and Christian Conti and Dunai Fuentes Hitos and Yunpu Hu and Farshad Khadivar and Raphaela Kreiser and Luz Martinez and Fabian Schilling and Ricardo Tapiador Morales and Guillem Torrente and Mario Ynocente Castro and Lison Abecassis and Alberto Giammarino and Yu-Ting Huang and Yannik Nagel and Andrea Scotti and Alexander Sigrist and Tiago Silva and Etienne Walther and Jengyan Wong and Bilan Yang and Asude Aydin and Divij Grover and Apurv Saha and Valentina Cavinato and Takekazu Kakinuma and Taishi Kunori and Valentin Monferrato and Stefan Richter and Stefanos Charalambous and Simon Guist and MadsAlber Kuhlmann-Jorgensen and Lorenzo Miele and Agis Politis and Mattia Scardecchia and Hiroaki Kitano and Peter R. Wurman and Peter Stone and Michael Spranger},
  title    = {Outplaying Elite Table Tennis Players with an Autonomous Robot},
  journal = {Nature},
  year     = {2026},
  abstract = {
              Artificial intelligence (AI) systems now challenge or
              surpass human experts in many computer
              games1,2. Physical and real-time sports such as table
              tennis, however, remain a major open challenge because
              of their requirements for fast, precise and adversarial
              interactions near obstacles and at the edge of human
              reaction time3. Here we present Ace, to our knowledge
              the first real-world autonomous system competitive with
              elite human table tennis players. Ace addresses the
              challenges of physical real-time interaction through a
              new, high-speed perception system using event-based
              vision sensors4, and a new control system based on
              model-free reinforcement learning, as well as
              state-of-the-art high-speed robot hardware. Evaluated in
              matches against elite and professional players under
              official competition rules, Ace achieved several
              victories and demonstrated consistent returns of
              high-speed, high-spin shots. These results highlight the
              potential of physical AI agents to perform complex,
              real-time interactive tasks, suggesting broader
              applications in domains requiring fast, precise
              human-robot interaction. },
  wwwnote={<a href="https://www.nature.com/articles/s41586-026-10338-5">The official paper from Nature</a><br>
      <a href="https://sonyresearch.github.io/ace_public/">The supplementary material</a></br>
      <a href="https://www.youtube.com/watch?v=FrGq8ltb-_E">A video about the project</a><br>
      <a href="https://ai.sony/blog/inside-project-ace-discover-the-robot-athlete-that-competes-with-professional-table-tennis-players">The project website</a>
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun May 03, 2026 18:20:38