Browsing by Subject "Motion planning"

Now showing 1 - 5 of 5

Open Access
A comparative study of five algorithms for processing ultrasonic arc maps
(2005) Kurt, Arda
In this work, one newly proposed and four existing algorithms for processing ultrasonic arc maps are compared for map-building purposes. These algorithms are the directional maximum, Bayesian update, morphological processing, voting and thresholding, and arc-transversal median algorithm. The newly proposed method (directional maximum) has a basic consideration of the general direction of the mapped surface. Through the processing of arc maps, each method aims at overcoming the intrinsic angular uncertainty of ultrasonic sensors in map building, as well as eliminating noise and cross-talk related misreadings. The algorithms are implemented in computer simulations with two distinct motion-planning schemes for ground coverage, wall following and Voronoi diagram tracing. As success criteria of the methods, mean absolute difference with the actual map/profile, fill ratio, and computational cost in terms of CPU time are utilized. The directional maximum method performed superior to the existing algorithms in mean absolute error, was satisfactory in fill ratio and performed second best in processing times. The results indicate various trade-offs in the choice of algorithms for arc-map processing.
Open Access
Motion control for realistic walking behavior using inverse kinematics
(IEEE, 2007-05) Memişoǧlu, Aydemir; Güdükbay,Uğur; Özgüç, Bülent
This study presents an interactive hierarchical motion control system for the animation of human figure locomotion. The articulated figure animation system creates movements using motion control techniques at different levels, like goal-directed motion and walking. Inverse Kinematics using Analytical Methods (IKAN) software, developed at the University of Pennsylvania, is utilized for controlling the motion of the articulated body. © 2007 IEEE.
Open Access
Motion planning of a mechanical snake using neural networks
(1998) Fidan, Barış
In this thesis, an optimal strategy is developed to get a mechanical snake (a robot composed of a sequence of articulated links), which is located arbitrarily in an enclosed region, out of the region through a specified exit without violating certain constraints. This task is done in two stages: Finding an optimal path that can be tracked, and tracking the optimal path found. Each stage is implemented by a neural network. Neural network of the second stage is constructed by direct evaluation of the weights after designing an efficient structure. Two independent neural networks are designed to implement the first stage, one trained to implement an algorithm we have derived to generate minimal paths and the other trained using multi-stage neural network approach. For the second design, the intuitive multi-stage neural network back propagation approach in the literature is formalized.
Open Access
Multi-stage neural networks with application to motion planning of a mechanical snake
(IEEE, 2003-06) Fidan, B.; Sezer, Erol; Akar, M.
An efficient approach to nonlinear control problems in which the plant is to be driven to a desired state using a neural network controller in a number of steps is by representing the whole process as a multi - stage neural network. In this paper, an explicit formulation of the back propagation algorithm is developed for such networks. Later, this approach is used to build up a path planner for a mechanical snake (a robot composed of a sequence of articulated links). This path planner, together with a tracking algorithm, is shown to get the mechanical snake out of a collision-free closed region.
Open Access
Using constrained intuitionistic linear logic for hybrid robotic planning problems
(IEEE, 2007) Saranlı, Uluç; Pfenning F.
Synthesis of robot behaviors towards nontrivial goals often requires reasoning about both discrete and continuous aspects of the underlying domain. Existing approaches in building automated tools for such synthesis problems attempt to augment methods from either discrete planning or continuous control with hybrid elements, but largely fail to ensure a uniform treatment of both aspects of the domain. In this paper, we present a new formalism, Constrained Intuitionistic Linear Logic (CILL), merging continuous constraint solvers with linear logic to yield a single language in which hybrid properties of robotic behaviors can be expressed and reasoned with. Following a gentle introduction to linear logic, we describe the two new connectives of CILL, introduced to interface the constraint domain with the logical fragment of the language. We then illustrate the application of CILL for robotic planning problems within the Balanced Blocks World, a "physically realistic" extension of the Blocks World domain. Even though some of the formal proofs for the semantic foundations of the language as well as an efficient implementation of a theorem prover are yet to be completed, CILL promises to be a powerful formalism in reasoning within hybrid domains. © 2007 IEEE.