Tham khảo tài liệu 'advances in robot navigation part 8', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Hybrid Approach for Global Path Selection Dynamic Obstacle Avoidance for Mobile Robot Navigation 129 White line sensor consists of a highly directional phototransistor for line sensing and red LED for illumination. Fig. 6 shows Fire Bird V mobile robot path selection results with convex shape obstacles in the proposed real time environment. Fig. 6. Fire Bird V Mobile Robot Real Time Navigation Results Fig. 7. Fire Bird V Mobile Robot Real Time Navigation Results 130 Advances in Robot Navigation 8. Conclusion Proposed method builds the test bed with Fire Bird V Mobile Robot for future development of an intelligent wheelchair for elderly people assistance in the indoor environment. Real time results proves DT computes the shortest path selection for the elderly people and movement of people any object was predicted in prior by DT and collision avoidance with objects was effectively handled by GJK Algorithm. The proposed framework in real time with Fire Bird V Mobile Robot control program is easily scalable and portable for any indoor environment with various shapes of obstacles it encounters during navigation. Proposed method was tested successfully with various shapes of dynamic obstacles. GJK Algorithm for computing the distance between objects shows the improved performance in simulation and real time results. The algorithm fits well especially for the collision detection of objects modelled with various types of geometric primitives such as convex obstacles. Unlike many other distance algorithms it does not require the geometry data to be stored in any specific format but instead relies solely on a support mapping function and using the result in its next iteration. Relying on the support mapping function to read the geometry of the objects gives this algorithm great advantage. The algorithm s stability speed and small storage footprint make it popular for real time collision detection. 9. Acknowledgement This work is part of Research grant sponsored by .
