Congratulations to Yulun Tian for being one of 5 innovators to share the 2019 AUVSI XCELLENCE Humanitarian Award. His work, Search and Rescue under the Canopy (SARUC), aims to locate humans and materials lost in challenging and cluttered forest areas.

Award Announcement

ACL co-authored 5 papers accepted to ICRA 2019! Congratulations to all authors.

Papers

• Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments
• Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning
• Efficient Constellation-Based Map-Merging for Semantic SLAM
• Safe Reinforcement Learning with Model Uncertainty Estimates
• Streaming Scene Maps for Co-Robotic Exploration in Bandwidth Limited Environments

Congrats to Shayegan Omidshafiei, Dong Ki Kim, Miao Liu, Gerald Tesauro, Matthew Riemer, Chris Amato, Murray Campbell for their paper Learning to Teach in Cooperative Multiagent Reinforcement Learning! They are looking forward to present and discuss the work at AAAI-19 this end of January.

System allows drones to cooperatively explore terrain under thick forest canopies where GPS signals are unreliable.

MIT News Article

ACL members (Björn Lütjens, Kris Frey, Macheng Shen, Michael Everett) have published works at IROS 2018!

Papers

• Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
• Transferable Pedestrian Motion Prediction Models at Intersections
• Safe Reinforcement Learning with Model Uncertainty Estimates (Spotlight Presentation in Workshop on Machine Learning in Robot Motion Planning)
• Planning Beyond The Sensing Horizon Using a Learned Context (Workshop on Machine Learning in Robot Motion Planning)

Congratulations to Shayegan Omidshafiei who has finished his PhD in Decentralized Teaching and Learning in Cooperative Multiagent Systems at ACL. Thanks for all the helpful advice to the first-years and best of luck at Google DeepMind in Paris!

Shayegan’s Homepage, Shayegan’s Thesis