What is SLAM and why is needed it?

Simultaneous Localization And Mapping, SLAM, is the action of navigating an environment while mapping it at the same time to create a local positioning system in which a robot can position itself in reference to its surroundings (Musba, 2013).  Why use a complicated system when GPS is available? There are many situations where GPS is not a viable option like indoors, or underwater. Focusing on the indoors application, a system can use a camera to detect, avoid and map obstacles by using SLAM (Egodagamage, 2017). While SLAM is not necessary as a technique to get an autonomous system to navigate without crashing, it is a necessary for more complex problems like remembering where an object of interest is. 

SLAM allows the unmanned system to create a map by referencing the observed obstacles, and surroundings and recording the data with reference to the system. As the system moves through an area more data is available creating a better map, and recording the position of the system with respect to the layout of a room (Egodagamage, 2017). By recording the position of objects on a map with respect to the unmanned system missions like retrieving an object of interest form one location to another, or remembering the entrance/exit of a room are possible. Utilizing a camera the system can record protrusions, obstacles and the layout of a room, but the key point is recognizing specific stitching points for the algorithm to overlap image sections in order to create a map (Egodagamage, 2017). Instead of one camera a 3D image can be created using multiple cameras to create a better distance approximation, recording and overlap (Yang, 2017).

While other methods of mapping and navigation are available like LIDAR and sonar, visual cameras are by comparison cheaper to obtain, mount and operate. Cameras are becoming the best sensor for robotics allowing small unmanned vehicles to identify obstacles, navigate unexplored environments, and map areas to perform complex missions. 




References

 Egodagamage, R. Tuceryan, M. (2017, January). Distributed monocular SLAM for Indoor map building. Journal of Sensors. Volume 2017.

Ibrahim Musba. (2013, September 10). Robot navigation using SLAM. [Video file] Retrieved from https://www.youtube.com/watch?v=SeNLUW79_-c

Yang, S. Scherer, S. Yi, X. Zell, A. (2017, July). Multi-camera visual SLAM for autonomous navigation of micro aerial vehicles. Robotics and Autonomous Systems. 93,  116-134.

Comments

  1. UnknownOctober 22, 2017 at 6:12 PM

    Felipe,

    This sounds like a great technology for home-use robots, such as the system you described which would be used indoors. Robotic housekeepers, nannies, and security systems could be able to navigate about the home safely using SLAM. Thanks for bringing it up!

    ReplyDelete
  2. UnknownOctober 22, 2017 at 6:19 PM

    Very interesting post. GNSS navigation seems to currently be the default choice for determining position in many of today's unmanned systems. Your entry brings up valid points. Alternate means like SLAM can reduce reliance on satellite reception and allow for operation in areas or environments that are not conducive to satellite navigation. It's interesting to see the shift in design approach to more closely mimic the way humans function. We rely heavily on our senses and the perception of our environment to navigate. Vision is arguably the most important sense for navigation, so it's no surprise visual systems are being developed for unmanned systems.

    ReplyDelete

Post a Comment

Popular posts from this blog

Image
GPS and IMU Replacement Using Stereovision in Small Unmanned Aerial Vehicles                         GPS is not effective indoors, and measuring systems like LiDAR are too big to be used on some small Unmanned Aerial Systems (sUAS) according to the developers of the Centeye (Barrows, 2016, 0:01-0:28). The idea of the Centeye is to use two light cameras for stereo vision on all four sides of the quadcopter to create a full 360ยบ field of view on which measurements of objects can be made (Centeye, n.d.a). The cameras used on the visual system are less than a 1cm (0.4in) long and weight less than 0.2 grams (0.000441lbs), so they can be installed on Nano quadcopters weighting in at 38 grams (0.0838lbs) (Centeye, n.d.a). While the small format CMOS sensor (Centeye RockCreek™ vision chips) is the heart of the Centeye, the whole sensor is made up of two of the trademark light sen...
Read more
Image
Complexity of ROV Control Stations           The biggest challenge when putting together a Remote Operated Vehicle (ROV)  control station is the variability in the market. In my research I could not find a single offering that could be plug and play, and instead every control station is a custom build  accommodating the different sensors and manipulators mounted on the robot. The cameras, sonar, lasers, and other sensors can be patch through using different equipment independently from the ROV controller. The nature of ROV, theater through physical wires to the control station, mean all sensors, motors, and manipulators are connected to their own hardware and software solution allowing operators to customize their station according to the specific components on the ROV. FMC Schilling Robotics, ROV Control Station. joysticks connected to a computer, and arm manipulator on the center under monitors. Monitors showing different s...
Read more
Image
Curiosity Needs to Ration Unlimited Power Power is limited on Mars and solar source won’t cut it when continuous reliable power source is needed. That is why the Curiosity Rover is powered by a Radioisotope Thermal Generator (RTG), a nuclear powered electric generator powered by Plutonium dioxide in a ceramic form (Jet Propulsion laboratory (JPL), 2016). The decaying radioactive material creates heat which is turn into electricity using thermocouples, and the total efficiency of the system is about 6% electric power conversion (JPL, 2016). The RTG on Curiosity can generate around 110 watts of steady electric power and this resource needs to be manage and rationed throughout the day scheduling critical aspects of the mission (LaMonica, 2016). Curiosity’s RTG will last up to 14 years, but the power output at a time is limited, and available power needs to be schedule to operate the sensors, the locomotion, and the data transfer.          ...
Read more