Human–Robot Interaction (HRI) using hand gesture recognition offers an effective and non-contact approach to enhancing operational intuitiveness and user convenience. However, most existing studies primarily focus on either static sign language recognition or the tracking of hand position and orientation in space. These approaches often prove inadequate for controlling complex robotic systems. This paper proposes an advanced HRI system leveraging dynamic hand gestures for controlling quadruped robots equipped with a robotic arm. The proposed system integrates both semantic and pose information from dynamic gestures to enable comprehensive control over the robot’s diverse functionalities. First, a Depth–MediaPipe framework is introduced to facilitate the precise three-dimensional (3D) coordinate extraction of 21 hand bone keypoints. Subsequently, a Semantic-Pose to Motion (SPM) model is developed to analyze and interpret both the pose and semantic aspects of hand gestures. This model translates the extracted 3D coordinate data into corresponding mechanical actions in real-time, encompassing quadruped robot locomotion, robotic arm end-effector tracking, and semantic-based command switching. Extensive real-world experiments demonstrate the proposed system’s effectiveness in achieving real-time interaction and precise control, underscoring its potential for enhancing the usability of complex robotic platforms.

In recent years, humanoid robot technology has been developing rapidly due to the need for robots to collaborate with humans or replace them in various tasks, requiring them to operate in complex human environments and placing high demands on their mobility. Developing humanoid robots with human-like walking and hopping abilities has become a key research focus, as these capabilities enable robots to move and perform tasks more efficiently in diverse and unpredictable environments, with significant applications in daily life, industrial operations, and disaster rescue. Currently, methods based on hybrid zero dynamics and reinforcement learning have been employed to enhance the walking and hopping capabilities of humanoid robots; however, model predictive control (MPC) presents two significant advantages: it can adapt to more complex task requirements and environmental conditions, and it allows for various walking and hopping patterns without extensive training and redesign. The objective of this study is to develop a bipedal robot controller using shooting method-based MPC to achieve human-like walking and hopping abilities, aiming to address the limitations of the existing methods and provide a new approach to enhancing robot mobility.