.png){kind=icon}
.png){kind=icon}
Return
A Framework for Hierarchical Perception-Action Learning Utilizing Fuzzy Reasoning
.png){kind=icon}
OA
AI
DOI：10.1109/TSMCB.2012.2202109.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Perception-action (P-A) learning is an approach to cognitive system building that seeks to reduce the complexity associated with conventional environment-representation/action-planning approaches. Instead, actions are directly mapped onto the perceptual transitions that they bring about, eliminating the need for intermediate representation and significantly reducing training requirements. We here set out a very general learning framework for cognitive systems in which online learning of the P-Amapping may be conducted within a symbolic processing context, so that complex contextual reasoning can influence the P-A mapping. In utilizing a variational calculus approach to define a suitable objective function, the P-A mapping can be treated as an online learning problem via gradient descent using partial derivatives. Our central theoretical result is to demonstrate top-down modulation of low-level perceptual confidences via the Jacobian of the higher levels of a subsumptive P-A hierarchy. Thus, the separation of the Jacobian as a multiplying factor between levels within the objective function naturally enables the integration of abstract symbolic manipulation in the form of fuzzy deductive logic into the P-A mapping learning. We experimentally demonstrate that the resulting framework achieves significantly better accuracy than using P-A learning without top-down modulation. We also demonstrate that it permits novel forms of context-dependent multilevel P-A mapping, applying the mechanism in the context of an intelligent driver assistance system.
Keywords:
Autonomous agents
fuzzy logic (FL)
hierarchical systems
machine learning
online learning
perception-action (P-A) learning
subsumption architectures
vehicle safety
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W