Robotic or Bio-inspired: A Comparison
The last four chapters have discussed the mapping and navigation problem and the range of system solutions that exist both in the animal world and on robot platforms. There are many forces driving the diversity that is apparent when examining these system
- PDF / 338,551 Bytes
- 6 Pages / 430 x 660 pts Page_size
- 18 Downloads / 193 Views
The last four chapters have discussed the mapping and navigation problem and the range of system solutions that exist both in the animal world and on robot platforms. There are many forces driving the diversity that is apparent when examining these systems. In nature, creatures and their navigation systems have evolved to suit their environments and their own physical and sensory characteristics. In the natural world, the range of body types, sensory equipment, environments, and lifestyles has produced a myriad of solutions to the problems facing a creature that needs to move around effectively in its environment. Likewise in the research labs of robotics researchers and the domestic home or industrial workplace, mapping and navigation systems have developed in ways to suit the environments, the sensors available and the purpose of the robot. Given this diversity it seems a challenging task to identify one research direction that is most likely to yield a complete robot mapping and navigation system. The specific mechanisms and representations of each system differ so greatly that direct comparison is not possible. Fortunately, there are a number of fundamental mapping and navigation issues that are common to all these systems. Through consideration of these issues for all these systems it is possible to define goals for future research in this field, and in the process identify one means by which these goals may be met. The following sections compare and contrast biological systems and models of biological systems with robotic mapping algorithms in a range of areas. The comparison highlights the shortcomings of both types of system as well as their complementary characteristics. These shortcomings are particularly relevant when considering where future research into the mapping and navigation problem should focus. After a discussion of possible future research approaches, the final section describes the line of research that was pursued in the work described in this book.
6.1 Robustness Versus Accuracy One of the most significant differences between biological mapping systems and probabilistic methods is the world representations that they use. Many probabilistic systems incorporate high resolution occupancy grid maps, such as those shown in Fig. 6.1. In work by Grisetti, Stachniss et al. (2005) in the Freiburg campus environment, the M.J. Milford: Robot Navigation from Nature, STAR 41, pp. 55–60, 2008. © Springer-Verlag Berlin Heidelberg 2008 springerlink.com
56
Robotic or Bio-inspired: A Comparison
occupancy grid contained 6.25 million squares. By contrast the place cells found in the rodent hippocampus appear quite coarse, and likely do not encode information to such a precise degree. Furthermore many probabilistic based mapping methods attempt to produce a Cartesian map with direct spatial correspondence to the physical environment. A 2.5 metre wide, 16.7 metre long corridor should appear as an identically sized region of free space in an occupancy grid map, with occupied cells along its edges. Biological
Data Loading...
