We present a new paradigm for real-time objectoriented SLAM with a monocular camera. Contrary to previous approaches, that rely on object-level models, we construct category-level models from CAD collections which are now widely available. To alleviate the need for huge amounts of labeled data, we develop a rendering pipeline that enables synthesis of large datasets from a limited amount of man...

1 We compared standard multiple-funnel, modified multiple-funnel, intercept panel and canopy malaise (SLAM) traps with top and bottom collecting cups for their effectiveness (species richness, rarity, abundance) at capturing Cerambycidae in eastern North America. 2 Experiments were conducted in New York, Louisiana, Massachusetts and Georgia in 2011 and 2012. A combination of pheromones and host...

Simultaneous localization and map-building (SLAM) continues to draw considerable attention in the robotics community due to the advantages it can offer in building autonomous robots. It examines the ability of an autonomous robot starting in an unknown environment to incrementally build an environment map and simultaneously localize itself within this map. Recent advances in computer vision hav...

In this paper we show that all processes associated to the move-sense-update cycle of EKF SLAM can be carried out in time linear in the number of map features. We describe Divide and Conquer SLAM, an EKF SLAM algorithm where the computational complexity per step is reduced from O(n) to O(n) (the total cost of SLAM is reduced from O(n) to O(n)). In addition, the resulting vehicle and map estimat...

In the simultaneous localization and mapping (SLAM) problem, a mobile robot must localize itself in an unknown environment using its sensors and at the same time construct a map of that environment. While SLAM utilizing costly (expensive, heavy and slow) laser range finders as a sensor has been very successful in both indoor and outdoor environments, large-scale SLAMwith cost-effective visionba...

Simultaneous Localisation and Mapping (SLAM) is a popular map building approach in autonomous mobile robotics. Because users demand faster and more effective algorithms, SLAM remains an active area of research. However, the increasing complexity of applications, such as the environments the algorithm is applied to, makes it difficult to debug, evaluate and optimise such algorithms. Our prelimin...

Both simultaneous localization and mapping (SLAM) and detection and tracking of moving objects (DTMO) play key roles in robotics and automation. For certain constrained environments, SLAM and DTMO are becoming solved problems. But for robots working outdoors, and at high speeds, SLAM and DTMO are still incomplete. In earlier works, SLAM and DTMO are treated as two separate problems. In fact, th...

Simultaneous Localization and Mapping (SLAM) involves creating an environmental map based on sensor data, while concurrently keeping track of the robot’s current position. Efficient and accurate SLAM is crucial for any mobile robot to perform robust navigation. It is also the keystone for higher-level tasks such as path planning and autonomous navigation. The past two decades have seen rapid an...

This paper applies a new constant-time, consistent and convergent Simultaneous Localization and Mapping (SLAM) algorithm to an autonomous underwater vehicle (AUV). A constant-time SLAM algorithm offers computation independent of workspace size and is one key component in the development of truly autonomous agents. The real-time deployment of such a system would be a landmark achievement for the...

The problem of learning a map with a mobile robot has been intensively studied in the past and is usually referred to as the simultaneous localization and mapping (SLAM) problem. However, most existing solutions to the SLAM problem learn the maps from scratch and have no means for incorporating prior information. In this paper, we present a novel SLAM approach that achieves global consistency b...