Steer angle fields: An approach to robust manoeuvring in cluttered, unknown environments

Bauer, Rudolf; Feiten, Wendelin; Lawitzky, Gisbert

doi:10.1016/0921-8890(94)90027-2

Cited by 21 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some approaches to achieving the goal of safe navigation in an unknown environment have been proposed, such as the method of combining certainty grids and potential fields in Borenstein and Koren [8], and the use of the Bug2 and Tarry algorithms in Skewis and Lumelsky [9]. Besides, Bauer et al [10] used the properties of geometry and kinematics for wheel control in an unknown environment.…”

Section: A Survey Of Related Studiesmentioning

confidence: 99%

“…The turning angle of the vehicle is limited in this study to be within thirty degrees to the left or right. It is computed as follows: min 2f030;K;30g jh(X i )j = min 2f030;...;30g jX T i QX i + V T X i j = min 2f030;...;30g j1m 2 i + 2mili + 3l 2 i + v1mi + v2lij (10) in which X i = [m i l i ] T and jh(X i )j specifies the absolute value of the sum of X T i QXi and V T Xi: According to the property of the quadratic classifier, if h(X) < 0; then X belongs to the left-hand side of h(X); if h(X) > 0; then X belongs to the right-hand side of h(X); and if h(X) = 0; then X falls on h(X): The closer the location specified by the coordinates (m i ; l i ) to the path h(X); the smaller the absolute value of h(X): Hence, m0 and l0 make the absolute value of h(X) minimum.…”

Section: Vehiclementioning

confidence: 99%

“…After getting the turning angle by (10), the vehicle immediately controls the front wheels to turn degrees and keeps moving forward until the next control command is received. It is in this way that the vehicle keeps on the collision-free path to achieve collision avoidance and navigation in real time.…”

Section: Vehiclementioning

confidence: 99%

See 2 more Smart Citations

Obstacle avoidance for autonomous land vehicle navigation in indoor environments by quadratic classifier

Tsai

1999

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

A vision-based approach to obstacle avoidance for autonomous land vehicle (ALV) navigation in indoor environments is proposed. The approach is based on the use of a pattern recognition scheme, the quadratic classifier, to find collision-free paths in unknown indoor corridor environments. Obstacles treated in this study include the walls of the corridor and the objects that appear in the way of ALV navigation in the corridor. Detected obstacles as well as the two sides of the ALV body are considered as patterns. A systematic method for separating these patterns into two classes is proposed. The two pattern classes are used as the input data to design a quadratic classifier. Finally, the two-dimensional decision boundary of the classifier, which goes through the middle point between the two front vehicle wheels, is taken as a local collision-free path. This approach is implemented on a real ALV and successful navigations confirm the feasibility of the approach.

show abstract

Section: A Survey Of Related Studiesmentioning

confidence: 99%

Section: Vehiclementioning

confidence: 99%

See 1 more Smart Citation

Obstacle avoidance for autonomous land vehicle navigation in indoor environments by quadratic classifier

Tsai

1999

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

show abstract

“…They are much simpler to implement than global planners, since they typically map the sensor readings directly to actions. Various examples include potential-field methods [1], [8], fuzzy logic approaches [7], [15], and specialized approaches [2], [3]. As with any local search method, local path-planners do not guarantee global convergence to the target since they may get trapped in local minima.…”

Section: Introductionmentioning

confidence: 99%

Sensory based motion planning with global proofs

Kamon

Rivlin

Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative R

View full text Add to dashboard Cite

Abstract-We present DistBug, a new navigation algorithm for mobile robots which exploits range data. The algorithm belongs to the Bug family, which combines local planning with global information that guarantees convergence. Most Bug-type algorithms use contact sensors and consist of two reactive modes of motion: moving toward the target between obstacles and following obstacle boundaries. DistBug uses range data in a new "leaving condition" which allows the robot to abandon obstacle boundaries as soon as global convergence is guaranteed, based on the free range in the direction of the target. The leaving condition is tested directly on the sensor readings, thus making the algorithm simple to implement. To further improve performance, local information is utilized for choosing the boundary following direction, and a search manager is introduced for bounding the search area. The simulation results indicate a significant advantage of DistBug relative to the classical Bug2 algorithm.The algorithm was implemented and tested on a real robot, demonstrating the usefulness and applicability of our approach.

show abstract