DCIST CRA
  • Home
  • The Team
  • Technical Thrusts
  • Meetings
  • News
  • Repository
  • Search
  • Menu Menu

The Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance (CRA) will create Autonomous, Resilient, Cognitive, Heterogeneous Swarms that can enable humans to participate in a wide range of missions in dynamically changing, harsh, and contested environments. These include search and rescue of hostages, information gathering after terrorist attacks or natural disasters, and humanitarian missions.

Swarms of humans and robots will operate as a cohesive team with robots preventing humans from coming in harms way (Force Protection) and extending and amplifying their reach to allow one human to do the work of ten humans (Force Multiplication). Our research will create swarms that will provide on-demand services in these missions.

DCIST graphic

  1. Swarms: DCIST research will develop the methodologies for architecting autonomous, resilient, cognitive, heterogeneous swarms of sensors, robots, and intelligent machines that can work with humans.
  2. Networking: Autonomous networking provides the backbone for perception, control, and learning in teams and is required in all three research areas: Distributed Learning, Heterogeneous Group Control, Adaptive and Resilient Behaviors.
  3. Intelligence: DCIST research will enable a novel class of intelligent agents that are able to learn and adapt to new environments and to other agents in a distributed way, and be adaptive and resilient to sudden changes and threats.
  4. Autonomy: Autonomy in individual agents and groups of agents requires distributed learning and perception, networking across individuals in the groups, and control of heterogeneous groups.
  5. Resilience: DCIST research will address resilience in heterogeneous groups, specifically in the context of changes in the environment, new threats to the team, and disruptions and intrusions in the network.
  6. Collaboration: Collaboration between autonomous agents and with humans requires distributed learning and control of heterogeneous agents, and enables resilience to sudden and catastrophic events.

Technical Thrusts

Abstract network of lines and dots, illustration

Distributed
Intelligence

Heterogeneous
Group Control

Adaptive and Resilient
Behaviors

Cross Disciplinary illustration

Cross-Disciplinary
Experimentation

News

Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

0 Comments
/
April 3, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/03/Screen-Shot-2020-03-23-at-11.37.02-AM.png 294 440 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-04-03 08:32:202020-03-23 15:39:47Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

Asymptotically Optimal Planning for Non-myopic Multi-Robot Information Gathering

0 Comments
/
March 27, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/03/rss2019.png 1100 2088 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-03-27 08:43:402020-03-11 15:56:34Asymptotically Optimal Planning for Non-myopic Multi-Robot Information Gathering

Active Exploration in Signed Distance Fields

0 Comments
/
March 20, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/03/icra_slide_pic.png 1250 1250 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-03-20 09:00:042020-03-09 14:53:12Active Exploration in Signed Distance Fields

Learning Multi-Agent Policies from Observations

0 Comments
/
March 13, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/03/overview_no_sections.png 839 1238 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-03-13 09:00:102020-03-04 18:43:05Learning Multi-Agent Policies from Observations

Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors

0 Comments
/
March 6, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/03/unnamed.jpg 549 977 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-03-06 09:00:392020-03-03 13:16:59Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors

Planning with Uncertain Specifications (PUnS)

0 Comments
/
February 28, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/02/puns.png 1080 1920 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-02-28 15:39:362020-02-28 15:39:36Planning with Uncertain Specifications (PUnS)

Synthesis of a Time-Varying Communication Network by Robot Teams with Information Propagation Guarantees

0 Comments
/
February 21, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/02/Screen-Shot-2020-02-21-at-12.20.23-PM.png 689 1402 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-02-21 17:21:542020-02-28 16:00:21Synthesis of a Time-Varying Communication Network by Robot Teams with Information Propagation Guarantees

Learning Decentralized Controllers with Graph Neural Networks

0 Comments
/
February 10, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/02/gnn_traj.png 784 1098 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-02-10 09:00:462020-02-07 17:53:27Learning Decentralized Controllers with Graph Neural Networks

Heterogeneity and Uncertainty in Perimeter Defense

0 Comments
/
February 8, 2020
Read more
https://www.dcist.org/wp-content/uploads/2020/02/problem_formulation.png 648 1280 Briana Tyson /wp-content/uploads/2018/04/DCIST-Black-340-x-126-padded.png Briana Tyson2020-02-08 09:00:002020-02-07 17:53:54Heterogeneity and Uncertainty in Perimeter Defense
PreviousNext

An Army Research Laboratory Collaborative Research Alliance

 
 
 
 
 
DCIST logo

CONTACT

Website: US Army Research Lab DCIST
Email: dcist@seas.upenn.edu
Login

Gov’t Login

DCIST Members Only

© Copyright - DCIST. Site by Academic Web Pages
Scroll to top