[Show abstract][Hide abstract] ABSTRACT: This paper extends the capabilities of the Evolutionary, Hybrid, PDEODE controller (EHPC) that is suggested in  for navigating an agent in an unknown, multidimensional, stationary environment. This is accomplished by m9difying the Hybrid, PDE-ODE controller (HPC) used in constructing the EHPC so that it can incorporate directional requirements among the set of constraints it is enforcing. Theoretical developments along with simulation results are provided.
[Show abstract][Hide abstract] ABSTRACT: Recently, the authors suggested a new class of Intelligent Motion Controllers that are called Evolutionary, Hybrid, PDEODE Controllers (EHPCs) . A controller of such a class is designed for the special task of guiding an agent in a fully unknown environment to a target set along an obstacle-free trajectory. In a short compaion paper, the authors breifly described an extension that would allow an EHPC to jointly condition a motion trajectory with both directional and region avoidance constraints . In this paper, an indepth investigation of the proposed extension is provideo[ Also, mathematical proofs of both convergence, and the ability to enforce directional and region avoidance constraints are supplied.
[Show abstract][Hide abstract] ABSTRACT: One of the most challenging problems in robotics is the design of navigators. Navigators are motion controllers that are used to generate a constrained solution trajectory linking a starting point to a target zone for an agent of arbitrary, unknown shape that is operating in an unknown environment. In other words, this class of controllers is required to carry out the unusual task of solving an ill-posed problem. This paper discusses the construction of a hybrid control structure that would enable an agent to successfully deal with the informationallydeprived situation that is described above. The control structure has an evolutionary nature that allows for Autonomous Structural Adaptation of the control relying only on a sequentially acquired sensory input as a source of information. It also has the ability tointegratc any available a priori information in its database, regardless of its fragmentation or sparsity, in the planning process to accelerate convergence. The slrueture is based on a bottom-up, Artificial Life approach to behavior synthesis that allows the integration ofexperienee along with synergy as drivers of the action select]on process. Theereheat development of the structure, a realization, and simulation results are provided.