Problem
Research questions and friction points this paper is trying to address.
robot arm control
cognitive map learners
inverse kinematics
phasor hypervectors
fractional power encoding
Robot Arm Control via Cognitive Map Learners
🤖 AI Summary
This work proposes a hierarchical, composable control framework for robotic arms based on Cognitive Map Learners (CMLs), addressing the limited generalizability of traditional inverse kinematics in multi-joint coordination tasks. Each joint is driven by an independent CML module that encodes target positions into phasor hypervectors via fractional power encoding. These representations are then decomposed into joint angles using either oscillator networks or modern Hopfield networks, eliminating the need for explicit inverse kinematics computation. The approach pioneers the application of arbitrarily composable CMLs to multi-joint manipulators, enabling zero-shot task generalization and dimensional scalability without retraining. High-precision target reaching is demonstrated on both 2D arms and 3D arms with rotating bases, confirming the framework’s versatility and efficacy.
📝 Abstract
Cognitive map learners (CML) have been shown to enable hierarchical, compositional machine learning. That is, interpedently trained CML modules can be arbitrarily composed together to solve more complex problems without task-specific retraining. This work applies this approach to control the movement of a multi-jointed robot arm, whereby each arm segment's angular position is governed by an independently trained CML. Operating in a 2D Cartesian plane, target points are encoded as phasor hypervectors according to fractional power encoding (FPE). This phasor hypervector is then factorized into a set of arm segment angles either via a resonator network or a modern Hopfield network. These arm segment angles are subsequently fed to their respective arm segment CMLs, which reposition the robot arm to the target point without the use of inverse kinematic equations. This work presents both a general solution for both a 2D robot arm with an arbitrary number of arm segments and a particular solution for a 3D arm with a single rotating base.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Cognitive Map Learners
Fractional Power Encoding
Phasor Hypervectors
Resonator Network
Inverse Kinematics-Free Control
🔎 Similar Papers
No similar papers found.
