Autonomous Decision and Control Laboratory
-
Algorithmic Contributions
- Scalable algorithms for partially observable Markov decision processes (POMDPs)
- Motion planning with safety guarantees
- Game theoretic algorithms
-
Theoretical Contributions
- Particle POMDP approximation bounds
-
Applications
- Space Domain Awareness
- Autonomous Driving
- Autonomous Aerial Scientific Missions
- Search and Rescue
- Space Exploration
- Ecology
-
Open Source Software
- POMDPs.jl Julia ecosystem
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10272214/pasted-from-clipboard.png)
PI: Prof. Zachary Sunberg
PhD Students
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8458281/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8458283/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8458284/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8458406/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/9421050/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10229532/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10273976/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/11106504/pasted-from-clipboard.png)
Postdoc
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/11106615/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10964509/aspen-and-hex.jpg)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8462117/rrbt_considerbelief.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10275503/hippo.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10964516/pasted-from-clipboard.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10964498/orbital.png)
POMDP Algorithms
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/9903364/pomdp-pb-mdp-2.png)
Machine learning components handle high-dimensional observations (e.g. images)
The ADCL's tree search algorithms solve realistic problems with continuous state, action and observation spaces.
The ADCL is a world leader in the development of scalable online algorithms for partially observable Markov decision processes (POMDPs)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10272864/ADCL-Black.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8832055/pasted-from-clipboard.png)
ADCL Members developed the first general analytical bounds on particle belief approximation error, indicating that algorithms with complexity independent of the state and observation space size are possible.
See cu-adcl.org/publications for related peer-reviewed and submitted papers.
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8047634/pasted-from-clipboard.png)
BOMCP
Voronoi Progressive Widening
POMCPOW
Applications
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10272864/ADCL-Black.png)
The algorithms that the ADCL develops are very general and effective in a wide range of applications including the following:
See cu-adcl.org/publications for related peer-reviewed and submitted papers.
Search and Rescue
- In collaboration with the COHRINT lab, we are developing a planner to automatically search an area for a lost or injured hiker with a multirotor aircraft.
Storm Science
- In collaboration with other RECUV researchers, we are developing algorithms for drones equipped with sensors to find paths within a storm that gather the most informative data.
Planetary Exploration
- In collaboration with NASA's jet propulsion lab, we are developing algorithms for safe autonomy for planetary exploration rovers.
Autonomous Driving
- Our algorithms can help autonomous vehicles safely interact with other road users such as pedestrians or human-driven cars.
Space Domain Awareness
- We have developed game-theoretic algorithms for deception-robust sensor tasking (next slide)
Explainable Decision Support
- In collaboration with the Johns Hopkins University Applied Physics Lab, we are developing methods for AI decision support algorithms to explain their conclusions and better understand what human operators want.
Ecology
- In collaboration with the University of California Berkeley, we have developed algorithms to plan rebuilding of ecosystems by adding key species sequentially.
Robotic Motion Planning
- In collaboration with other RECUV researchers, we have developed algorithms for safe motion planning under uncertainty.
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10275503/hippo.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10275509/planning.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/8462117/rrbt_considerbelief.png)
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10954310/output.png)
Game Theory
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10272864/ADCL-Black.png)
A new application area for the ADCL is game theory. When rational agents have different goals, optimization can no longer represent their behavior. Instead, game theory provides a mathematical framework for reasoning about how rational agents interact.
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/9348773/pasted-from-clipboard.png)
- In partially-observable domains, agents with opposing goals may try to outsmart each other by acting unpredictably. This type of behavior is captured in the game theoretical concept of a mixed Nash equilibrium.
- Algorithms for calculating mixed Nash equilibria are mostly limited to tabletop games such as Poker - new algorithms are needed to find these solutions in physical problems.
- ADCL members have applied this theory to a space domain awareness game to calculate stochastic surveillance strategies (in the figure at left) that deter a satellite from taking action in a sensitive region (green) by increasing the probability of detection.
See cu-adcl.org/publications for related peer-reviewed and submitted papers.
![](https://s3.amazonaws.com/media-p.slid.es/uploads/870752/images/10964498/orbital.png)
ADCL Summary
By Zachary Sunberg
ADCL Summary
- 240