Sukoya Tawaratsumida

About

Sukoya Tawaratsumida is a robotics researcher whose work has made significant contributions to the field of vision-based reinforcement learning for autonomous robot behavior acquisition. Their research centers on enabling mobile robots to learn purposive behaviors directly from visual input, without requiring pre-programmed knowledge of environmental parameters or robot kinematics — a genuinely ambitious goal for the era in which it was pursued. Their most influential work, "Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning" (1996), has accumulated 277 citations and established a foundational framework for applying Q-learning to real robotic systems equipped with vision sensors. This research demonstrated that robots could autonomously learn complex tasks — such as shooting a ball into a goal — purely through trial-and-error interaction with their environment. Building on this foundation, Tawaratsumida's subsequent work tackled the challenge of coordinating multiple independently learned behaviors to accomplish composite tasks, and explored adversarial scenarios involving obstacle avoidance in soccer-playing contexts. These contributions collectively address core challenges in autonomous robotics, including the perceptual aliasing problem and multi-behavior integration. With a cumulative citation count exceeding 500, their work remains a meaningful reference point for researchers working at the intersection of robot learning and computer vision.

Research Focus

Key Achievements

Top Papers

1. 1
   Purposive behavior acquisition for a real robot by vision-based reinforcement learning

   277 citations · 1996
2. 2
   Coordination of multiple behaviors acquired by a vision-based reinforcement learning

   71 citations · 2002
3. 3
   Vision-based reinforcement learning for purposive behavior acquisition

   71 citations · 2002
4. 4
   Vision-based behavior acquisition for a shooting robot by using a reinforcement learning

   33 citations · 2002
5. 5
   Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning

   27 citations · 1996
6. 6
   Learning in robotics. Purposive Behavior Acquisition for a Robot by Vision-Based Reinforcement Learning.

   21 citations · 1995
7. 7
   A Vision-Based Reinforcement Learning For Coordination Of Soccer Playing Behaviors

   9 citations · 2004
8. 8
   Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning

   6 citations · 1996

Key Collaborators

Contact & Links