Inverse Kinematics for Humanoid Robots Using Artificial Neural Networks
The area of inverse kinematics of robots, mainly manipulators, has been widely researched, and several solutions exist. The solutions provided by analytical methods are specific to a particular robot configuration and are not applicable to other robots. Apart from this drawback, legged robots are inherently redundant because they need to have real humanoid configurations. This degree of redundancy makes the development of an analytical solution for the inverse kinematics practically unapproachable. For this reason, our proposed method considers the use of artificial neural networks to solve the inverse kinematics of the articulated chain that represents the robot’s legs. Since the robot should always remain stable and never fall, the learning set presented to the artificial neural network can be conveniently filtered to eliminate the undesired robot configurations and reduce the training process complexity.
KeywordsHumanoid Robot Inverse Kinematic Zero Moment Point Roll Axis Postural Scheme
Unable to display preview. Download preview PDF.
- 7.Kurematsu, Y., Maeda, T., Kitamura, S.: Autonomous trajectory generation of a biped locomotive robot. In: IEEE Int. Conf. on Neural Networks, pp. 1961–1966 (1993)Google Scholar
- 8.Yamasaki, F., Miyashita, T., Matsui, T., Kitano, H.: PINO, The humanoid that walk. In: Proc. of The First IEEE-RAS Int. Conf. on Humanoid Robots (2000)Google Scholar
- 10.Hirai, K., et al.: The development of Honda humanoid robot. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, pp. 1321–1326 (1998)Google Scholar
- 11.Espiau, B., Sardain, P.: The antropomorphic biped robot BIP2000. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, pp. 3996–4001 (2000)Google Scholar
- 12.Kaneko, K., et al.: Design of prototype humanoid robotics platform for HRP. In: Proc. of the IEEE-RSJ Int. Conf. on Intelligent Robots and Systems, pp. 2431–2436 (2002)Google Scholar