Development of a fuzzy logic based mobile robot for dynamic obstacle avoidance and goal acquisition in an unstructured environment

Autonomous Navigation Applying Dynamic-Fuzzy Cognitive Maps and Fuzzy Logic

“…By analyzing the results in figure 3a and 3b we note that the robot takes the correct decisions. In second case, one dynamic obstacle is in the scenario starting about in position (10,83) and finishing about in position (3,83), figure 4a and 4b show the correct decisions in all maneuvers. In both cases, the robot motion trend is to move straight to the end point, but an.…”

“…The kinematic equations simulating the robot dynamic behavior has been inspired by [10] and uses scale in centimeters. In fact, the simulated robot corresponds to a mobile platform with two motors, and three sensors, one frontal, and one in each side.…”

“…These events must change mobile behavior. There are various works in the literature that model heuristic knowledge necessary for decision-making in autonomous navigation, by means of Fuzzy systems [9], [10], [11], [12], [13] and [14]. In a similar way, the approach proposed in this paper is to build qualitative models to mobile navigation by means of fuzzy systems.…”

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

“…To date, definition of fuzzy logic controller rules in robot obstacle avoidance are usually based on Mamdani or Takagi-Sugeno-Kang (TSK) rule base system [9][10][11][12]. However, it is difficult to maintain the correctness, consistency, and completeness of the generated fuzzy rule base.…”

Hybrid Control Techniques for Static and Dynamic Environments: a Step towards Robot-Environment Interaction

“…These can be identified as the inputs coming from different sensors (laser or camera scan and so on) or coming from more sophisticated devices like trackers (Harville & Li, 2004). The position of the multiple tracked objects is passed over time to the control algorithm which computes the correct speed override according to the combination of the Bayesian occupancy grid controller (Moravec & Elfes, 1985;Fulgenzi et al, 2007;Vasquez et al, 2006) and the fuzzy logic filter (Dong et al, 2005;Yen & Pfluger, 1995;Malhotra & Sarkar, 2005). In order to model the uncertainty coming from the sensors, a valid framework has to be taken into account; the Bayesian framework has suited models to cope with the uncertainty on the position of the obstacles but it also has an intrinsic capability to perform sensor fusion.…”