A Framework for Hierarchical Perception–Action Learning Utilizing Fuzzy Reasoning

Abstract

Abstract-Perception-Action (P-A) learning is an approach to cognitive system building that seeks to reduce the complexity associated with conventional environment-representation/actionplanning 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-A mapping 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 on-line learning problem via gradient descent using partial derivatives. Our central theoretical result is to demonstrate topdown 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 perception-action learning without top-down modulation. We also demonstrate that it permits novel forms of context-dependant multi-level P-A mapping, applying the mechanism in the context of an intelligent driver assistance system.

Emergent Intentionality in Perception-Action Subsumption Hierarchies

“…The agent thus progressively arrives at a set of novel percepts that relate directly to the agent's action capabilities in relation to the constraints of the environment (i.e., the environment's affordances); the agent learns to perceive only that which it can change. More accurately, the agent learns to perceive only that which it hypothesizes that it can change-thus, the set of experimental data points ∪ipi ⊂ S can, in theory, be generalized over so as to create an affordance-manifold that can be mapped onto the action space via the injective relation {actions} → {perceptinitial} × {perceptfinal} Kittler, 2008, 2010;Windridge et al, 2013a).…”

“…This centers on the fact that the learned manifold embodying the injective relation {actions} → {perceptinitial} × {perceptfinal} represents a constrained subset of the initial action domain, and as such, is susceptible to parametric compression. Furthermore, this parametric compression in the action domain (corresponding to the bootstrapping of a higher level action) necessarily corresponds to a parametric compression in the perceptual domain (P-A learning enforces a bijective relation { } { } { } initial new final new actions percept percept ↔ × such that each hypothesizable action (i.e., intention primitive) has a unique, discriminable outcome Kittler, 2008, 2010;Windridge et al, 2013a)).…”

“…An example utilizing a two-layer P-A hierarchy is given in Windridge et al (2013a) which incorporates a fuzzy first-order logic reasoning process on the top level and an Euler-Lagrangebased trajectory optmization process on the lower level. The fuzzy-reasoning process employs predicates embodying the P-A bijectivity condition to compute the fixed point of the logical operator TP; i.e., TP(I) = I for each time interval t.…”

Visual autonomous road following by symbiotic online learning

“…For instance, if we are approaching an intersection and the current control signal distribution has three modes (corresponding to left, straight and right), the prior distribution for 'left' will strengthen the mode for turning left, whereas the other two will be reduced. A similar approach has been proposed for directing the attention in driver assistance systems [24].…”

Finding the Real Surge Boundaries of Turbo-charged Automobiles Using Intelligent Fuzzy Reasoning Technique

“…Fuzzy logic set (FLS) has been adopted as a practical means to represent physical systems with uncertainties. The fuzzy logic controllers have its widest applications in recent decades [1,[10][11][12][13][14][15][16][17]. The FLS can also be applied for reasoning purpose in industrial applications, such as automobiles control, robot control, industrial instrumentation control, air quality monitoring, wastewater treatment, power control, artificial intelligence and expert systems, etc, and some non-control applications comprising, for example, image processing and data mining [2,3,5,11,12,18,19].…”