6 papers
PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM
Yanlong Ma, Nakul S. Joshi, Christa S. Robison +2
Loop closure is essential to reduce drift and build globally consistent maps in large-scale environments. However, reliable loop closure with only geometric information from, e.g.,…
OptMap: Geometric Map Distillation via Submodular Maximization
David Thorne, Nathan Chan, Christa S. Robison +2
Autonomous robots rely on geometric maps to inform a diverse set of perception and decision-making algorithms. As autonomy requires reasoning and planning on multiple scales, each…
Geometric Multi-Session Map Merging with Learned Local Descriptors
Yanlong Ma, Nakul S. Joshi, Christa S. Robison +2
Multi-session map merging is crucial for extended autonomous operations in large-scale environments. In this paper, we present GMLD, a learning-based local descriptor framework for…
Learning Smooth State-Dependent Traversability from Dense Point Clouds
Zihao Dong, Alan Papalia, Leonard Jung +4
A key open challenge in off-road autonomy is that the traversability of terrain often depends on the vehicle's state. In particular, some obstacles are only traversable from some o…
Submodular Optimization for Keyframe Selection & Usage in SLAM
David Thorne, Nathan Chan, Yanlong Ma +3
Keyframes are LiDAR scans saved for future reference in Simultaneous Localization And Mapping (SLAM), but despite their central importance most algorithms leave choices of which sc…
LiDAR Inertial Odometry And Mapping Using Learned Registration-Relevant Features
Zihao Dong, Jeff Pflueger, Leonard Jung +5
SLAM is an important capability for many autonomous systems, and modern LiDAR-based methods offer promising performance. However, for long duration missions, existing works that ei…