Michigan highlights at IROS 2020
The International Conference on Intelligent Robots and Systems (IROS) is free to access this year, giving anyone a look into the latest robotics research. Presentations and workshops will be on-demand, starting October 25th, allowing attendees to view the research they desire at any time.
Workshops
From Michigan, there are several faculty participating in workshops, including:
- Robotics-Inspired Biology with Talia Moore
- State of the Art in Robotic Leg Prostheses: Where We Are and Where We Want to Be with Bobby Gregg and Elliott Rouse
- MIT Mini-Cheetah Workshop with Jessy Grizzle and Maani Ghaffari
- Benchmarking Progress in Autonomous Driving with Ed Olson
- Mechanisms and Design: from Inception to Realization with Elliott Rouse
- Managing Deformation: A Step Towards Higher Robot Autonomy with Dmitry Berenson
Papers
In addition, several students and researchers are presenting their work:
- Low Latency Trajectory Predictions for Interaction Aware Highway Driving
Cyrus Anderson, Ram Vasudevan, Matthew Johnson-Roberson
[arXiv] [IEEE Xplore] [code] - Polylidar – Polygons From Triangular Meshes
Jeremy Castagno, Ella Atkins
[IEEE Xplore] [code] - Parts-based articulated object localization in clutter using belief propagation
Jana Pavlasek, Stanley Lewis, Karthik Desingh, Odest Chadwicke Jenkins
[arXiv] [video] [talk] [website] - TSBP: Tangent space belief propagation for manifold learning
Thomas Cohn, Odest Chadwicke Jenkins, Karthik Desingh, Zhen Zeng
[IEEE Xplore] [video] [website] - Monocular Depth Prediction through Continuous 3D Loss
Minghan Zhu, Maani Ghaffari, Yuanxin Zhong, Pingping Lu, Zhong Cao, Ryan M. Eustice, Huei Peng
[arXiv] [video] [code] - Heterogeneous Vehicle Routing and Teaming with Gaussian Distributed Energy Uncertainty
Bo Fu, William Smith, Denise Rizzo, Matthew Castanier, Kira Barton
[arXiv] [video] - Image Transformation and CNNs: A Strategy for Encoding Human Locomotor Intent for Autonomous Wearable Robots
Ung Hee Lee, Justin Bi, Rishi Patel, David Fouhey, Elliott Rouse
[IEEE Xplore] [code to be released at Michigan AI Symposium] - Unsupervised Pedestrian Pose Prediction — A deep predictive coding network-based approach for autonomous vehicle perception
Xiaoxiao Du, Ram Vasudevan, Matthew Johnson-Roberson
[IEEE Xplore] [video] [talk] [code] - SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images
Gideon Billings, Matthew Johnson-Roberson
[arXiv] [IEEE Xplore] [IROS Video Link]