Perception and Action in Dynamic Environments

ICRA 2021 Full Day Workshop

Overview

Humans and animals have an innate capacity to make predictions about their surroundings, which allows them to react to both static and dynamic obstacles during an action. Thanks to this ability, for example, a seagull can catch a fast-moving fish in a short amount of time. In contrast, artificial agents struggle to interact with complex and dynamic environments and often rely either on the assumption that the world is static or on simplified motion models of their surroundings. This workshop will bring together researchers coming from different backgrounds (computer vision, machine learning, and robotics) and applications, to discuss existing solutions, research problems, and the way forward to make robots interact with a permanently moving world. Besides the usual mix of invited talks and poster presentations, we will organize the DodgeDrones challenge, where participants will need to develop perception and control algorithms to navigate a drone in highly dynamic environments.

We have posted the entire workshop event on youtube! The event was extremely successful with over 200 participants. Feel free to follow @antoniloq on Twitter for follow-up workshops!

Invited Speakers

Program

Time Title Speakers
15:00 BST Welcome
15:10 BST From SLAM to Spatial Perception with 3D Dynamic Scene Graphs (YouTube) Luca Carlone (MIT)
15:30 BST Learning Agile Flight (YouTube) Davide Scaramuzza and Antonio Loquercio (U. Zurich)
15:50 BST Open Frontiers in Autonomous Flight (YouTube) Hayk Martiros (Skydio Autonomy)
16:10 BST Panel Discussion 1 (YouTube)
16:30 BST Winner of DodgeDrones Challenge and Presentations of Submitted Papers Oral presentations and live Q&A
17:00 BST Tactile Perception for Physical Human-Robot Interaction (YouTube) Katherine J. Kuchenbecker (Max Planck Institute for Intelligent Systems)
17:20 BST Towards Autonomous Agents at Scale (YouTube) Aleksandra Faust (Google Brain)
17:40 BST Robots that Anticipate and Adapt to Change (YouTube) Chelsea Finn and Annie Xie (Stanford)
18:10 BST Panel Discussion 2 (YouTube)
18:30 BST From HD Maps to No Maps for Autonomous Driving (YouTube) Wolfram Burgard (U. Freiburg and TRI)
18:50 BST Perception and Action for Self-Driving (YouTube) Raquel Urtasun (U. Toronto)
19:10 BST Towards Physically Predictive Models of Reality from Ego-centric Data (YouTube) Richard Newcombe (Facebook Reality Labs)
19:30 BST Panel Discussion 3 and Conclusions (YouTube)

Organizers