David Paz, Cassie Qiu, Jiaming Hu, Henry Zhang, and Michelle Sit completed their respective Master of Science degrees. David, Cassie, Jiaming and Henry will be continuing for their PhD, while Michelle will be starting a new career in the industry. Congratulations everyone!
Shengye Wang recently defended his PhD thesis titled “Reliability Engineering for Long-term Autonomous Service Robots”. He will be starting a new adventure in his life at Waymo. Congratulations Shengye!
Carlos Nieto-Granda recently defended his PhD thesis titled “Robust Distributed Multi-Robot Information Based Exploration and Sampling”. He will be starting a new adventure in his life at ARL. Congratulations Carlos!
Very excited to present THREE papers at IROS. The research covers topics from machine learning for place recognition, designing taxonomy for human-robot teams, and enabling robust logging mechanism for robots using blockchains. Check out Publications page for more information!
Very excited to present TWO papers at FSR. The research covers topics on deploying autonomous vehicles in campus environment and long-term TritonBot development. Check out Publications page for more information!
Shixin Li, James Smith, Po-jung Lai, Sumit Binnani, Vasudharini Mannar, and Anwesan Pal completed their respective Master of Science degrees. Shixin, James, Po-jung, Sumit and Vasu will be starting a new career in industry, while Anwesan will be continuing for his PhD. Congratulations everyone!
Very excited to present THREE papers at ICRA. The research covers topics from information based adaptive sampling, understanding modes of human-robot interaction, and using gestures to control a UAV. Check out Publications page for more information!
We present an efficient and scalable algorithm for seg- menting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving window over several point clouds to group similar regions over a graph, resulting in an initial over-segmentation. These regions are then merged to yield a dendrogram us- ing agglomerative clustering via a minimum spanning tree algorithm. Bipartite graph matching at a given level of the hierarchical tree yields the final segmentation of the point clouds by maintaining region identities over arbitrarily long periods of time. We show that a multistage segmentation with depth then color yields better results than a linear com- bination of depth and color. Due to its incremental process- ing, our algorithm can process videos of any length and in a streaming pipeline. The algorithm’s ability to produce robust, efficient segmentation is demonstrated with numer- ous experimental results on challenging sequences from our own as well as public RGBD data sets.Continue reading
Simultaneous Localization and Mapping (SLAM) is not a problem with a one-size-fits-all solution. The literature includes a variety of SLAM approaches targeted at different environments, platforms, sensors, CPU budgets, and applications. We propose OmniMapper, a modular multimodal framework and toolbox for solving SLAM problems. The system can be used to generate pose graphs, do feature-based SLAM, and also includes tools for semantic mapping. Multiple measurement types from different sensors can be combined for multimodal mapping. It is open with standard interfaces to allow easy integration of new sensors and feature types. We present a detailed description of the mapping approach, as well as a software framework that implements this, and present detailed descriptions of its applications to several domains including mapping with a service robot in an indoor environment, large- scale mapping on a PackBot, and mapping with a handheld RGBD camera.