3D SLAM: the grand challenge and ultimate goal for robotic perception.

Real-world applications in GPS-denied environments require robust mapping and perception techniques to enable mobile systems to autonomously navigate complex 3D environments.

Robotic environments are in general 3D, involving translation in three directions, x, y, and z, and rotation around three axes, roll, pitch, and yaw.

The challenge of lifelong SLAM in unstructured and dynamic 3D environments is however very much an open question.

The complexity of 3D SLAM is not as simple as estimating three more parameters. This is mainly because most sensory information lacks full 3D perception, and therefore, it becomes challenging to estimate parameters that are not observable directly. Moreover, if sensors exist to provide full 3D information, the complexity of processing algorithms increases significantly.

The problem of lifelong mapping in a dynamic 3D environment is very challenging, and compared with the static SLAM problem. The most significant challenge is to provide a method for keeping spatial representations up to date in environments that change across a range of time scales.

How to solve these challenge problems in 3D SLAM for autonomous robots?


For further info, please read the following references.

Saeedi, Sajad, Michael Trentini, Mae Seto, and Howard Li. “Multiple‐Robot Simultaneous Localization and Mapping: A Review.” Journal of Field Robotics 33, no. 1 (2016): 3-46.

Yang, Guang-Zhong, Jim Bellingham, Pierre E. Dupont, Peer Fischer, Luciano Floridi, Robert Full, Neil Jacobstein et al. “The grand challenges of Science Robotics.” Science Robotics 3, no. 14 (2018): eaar7650.

What is the future of grand challenges for robot navigation and exploration in extreme environments?

Saputra, Muhamad Risqi U., Andrew Markham, and Niki Trigoni. “Visual SLAM and Structure from Motion in Dynamic Environments: A Survey.” ACM Computing Surveys (CSUR)51, no. 2 (2018): 37.

Cadena, Cesar, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, José Neira, Ian Reid, and John J. Leonard. “Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age.” IEEE Transactions on Robotics 32, no. 6 (2016): 1309-1332.