Unbounded Motion Optimization by Developmental Learning

Abstract

An algorithm is presented for autonomous motion development with unbounded waveform resolution. Rather than a single optimization in a very large space, memory is built to support incremental improvements; therefore, complexity is balanced by experience. Analogously, human development manages complexity by limiting it during initial learning stages. Motions are represented by cubic spline interpolation; therefore, the development technique applies broadly to function optimization. Adding a node to the splines allows all previous memory samples to transfer to the higher dimension space exactly. The memory-based model, which is a locally weighted regression (LWR), predicts the expected outcome for a motion and provides gradient information for optimizing the motion. Results are compared against bootstrapping a direct optimization (DO) on a mathematical problem. Additionally, the method has been implemented to learn voltage profiles with the lowest peak current for starting a motor. This method shows practical accuracy and scalability.

Enhanced Robotic Hand–Eye Coordination Inspired From Human-Like Behavioral Patterns

“…where, d i is the distance from the retina structure center to each retina cell's center; i denotes the indices of the inner and outside areas; i ∈ [2,3]; i = 2 is the inner area, and i = 3 is the outside area. The parameters d o and µ are used to set the size and position of each cell.…”

“…In addition, the LWPR networks are widely used to implement robotic internal representations, e.g. [3], [43], [44]. …”

Evaluation and Transformation of Unrealizable Tasks for Robot Systems in Representation Space

“…The R-space is grided with a set of discretized parameters [21], [22] and the optimal path between ξ S and ξ G is searched by A* algorithm in the discretized R-space [24].…”

“…R-space-based method has been proposed to deal with the evaluations of the realizability for a prescribed task before it is truly executed [19]- [21]. Efficiency in recognizing optimal realization procedures is also validated for different tasks [22], [23]. However, more emphasis is located on recognizing optimal schemes for realizable tasks instead of fixing unrealizable tasks.…”