Intelligent learning and control of autonomous robotic agents operating in unstructured environments

Abstract

The control of autonomous intelligent robotic agent operating in unstructured changing environments includes many objective difficulties. One major difficulty concerns the characteristics of the environment that the agent should operate in. In unstructured and changing environments the inconsistency of the terrain, the irregularity of the product and the open nature of the working environment result in complex problems of identification, sensing and control.Problems can range from the effects of varying environmental conditions on the robot sensors and traction performance through to the need to deal with the presence of unexpected situations. Another major challenge is the large amounts of uncertainty that characterises real-world environments. On the one hand, it is not possible to have exact and complete prior knowledge of these environments. On the other hand, knowledge acquired through sensing is affected by uncertainty and imprecision. The quality of sensor information is influenced by sensor noise, the limited field of view, the conditions of observation, and the inherent difficulty of the perceptual interpretation process.Because environments and users of systems continuously change, robotic agents have to be adaptive. Intelligence helps because it gives systems the capacity to adapt more rapidly to environmental changes or to handle much more complex functions. In his paper we introduce this special issue and introduce the difficulty robots are facing in unstructured environments and how learning and computational intelligence can help the robots to adapt and give them the necessary intelligence they to face the challenges they encounter in their environments.

Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

“…Neural networks are frequently used in such a setting as they are especially amenable to evolutionary search for beneficial compositions of connection weights and network topology -generally termed neuro-evolution -and have been shown to generate high-performance controllers. Hagras and Sobh (2002) evolve spiking networks for online robot control. Full topology-plus-weight evolution is used for both monolithic (Clune et al, 2009) and ensemble (Howard et al, 2010) controllers.…”

Fuzzy optimisation based symbolic grounding for service robots

“…(Hagras and Sobh, 2002). For example, the localisation and navigation of the robot base suffered from sensor impressions.…”

“…Results show that the fluctuations that are most likely to occur during Levenberg-Marquardt training are damped out. Hagras et al (2002Hagras et al ( , 2004) presented a novel Fuzzy-Generic technique for the online learning and adoption of a fuzzy controller which can be applied to an intelligent robotic navigator. Fuzzy-Genetic is a life-long learning technique that enables the robot to navigate in changing environments where it adapts itself to the environment by tuning the controller rules that did not perform well.…”

Novel Laser-Based Obstacle Detection for Autonomous Robots on Unstructured Terrain

“…Mobile robots used for rescue and space exploration, etc. operate in dynamic and unstructured environments and face huge challenges due to the inherent uncertainties and the unpredictable conditions [ 3 ]. To achieve stable and robust operations, researchers have to develop many decision-making, autonomous navigation, and control algorithms [ 4 , 5 , 6 ].…”