Overview of Autonomous Systems LaboratoryMarco Pavone Autonomous Systems Laboratory Department of Aeronautics and AstronauticsStanford University

PTV Scientific Advisory BoardWinter meeting

January 10, 2016

Autonomous Systems LabASL

About MeBio:• Assistant Professor (2012 - present),

Stanford University, Aeronautics and Astronautics • Research Technologist (2010 - 2012),

NASA JPL, Robotics Section• Ph.D. in Aeronautics and Astronautics (2010),

Massachusetts Institute of Technology• BS and MS in Computer Science (2005),

University of Catania and Scuola Superiore of Catania

Highlights: • Research interests: robotics, optimization, intelligent transportation systems• PECASE Award (2017)• NSF CAREER Award (2015)• NASA Early Career Faculty Award (2012)• Invited to the White House and the US Senate to speak on autonomous vehicles • Best paper nominations/awards at Field and Service Robotics Conference (2015), at

Robotics: Science and Systems Conference (2014), and at NASA symposia (2015)

Autonomous Systems

Autonomous Systems

Courtesy of Google Courtesy of Amazon

Courtesy of DARPA Courtesy of JPL

Autonomous Systems

• Automation: system limited to specific actions for pre-programmed situations

How can we endow a machine with the capability of making rapid and reliable decisions without knowing a priori all situations that might occur?

• Autonomy: system reacts to situations that were not pre-programmed or anticipated at the design stage

Courtesy of FIAT Courtesy of eHang

Research Synopsis

Machine LearningReal-Time Control/Optimization

Distributed Computing

Enabling Technologies

Research Areas

Controlling Individual AS:- Robotic Motion Planning

- Risk-Sensitive Decision-Making

Deploying AS:- Autonomous Spacecraft/Space Robots- Autonomous Transportation Networks

Autonomous Systems (AS)Key Approach:

Optimization-Based Control

Controlling Networked AS:- Task-Based Coordination of Robots

- Complexity Theory for Robotic Networks

Agile Autonomous Systems

In collaboration with Toyota, Northrop Grumman, and Qualcomm

Autonomous Mobility-on-DemandVehicle Autonomy Car Sharing

+"Autonomous Mobility-On-Demand (AMoD)

Research objectives: 1. Modeling: stochastic models for tractable analyses2. Control: real-time routing of autonomous vehicles at a city-wide scale3. Applications: case studies and technology infusion

How to Control a Fleet of Autonomous Vehicles?Problem falls under the general class of networked, heterogeneous, stochastic decision problems with uncertain information:• Problem Data / Model: travel demand, road network• Control inputs: vehicle routing, passenger loading/unloading• Outputs: customer waiting times, customer queue lengths, etc.

Key features:Static version NP-hard Dynamics add queueing phenomena

Closed system:cascade feedback effects

Closed-loop control policies aimed at optimal throughput

SystemController

A Family of Models for Control and Evaluation

Distributed queueing-theoretical models

Lumped queueing-theoretical models

(Stochastic) MPC models

Macroscopic Microscopic

Analytical Computational

Overarching goals: 1. Theoretical insights and guidelines for system design2. Real-time control algorithms3. Formal guarantees for stability and performance

[Pavone, MIT ’10], [Treleaven, Pavone and Frazzoli, TAC ’13]

[Pavone, Smith, Frazzoli, Rus, IJRR ’12],[Zhang, Pavone, IJRR ’15][Zhang, Rossi, Pavone, RSS ‘16]

[Zhang, Rossi, Pavone, ICRA ’16]

Complements simulation-based methods such as [Osorio, Bierlaire, OR ’13], [Fagnant, Kockelman, TR C ’14], [Fagnant, Kockelman, Bansal, JTRB ’15], [Shen, Lopes, PRIMA ’15].Leverages vast literature on VRP [Toth, Vigo, ’14], DTA [Janson, TRB, ’91], and queueing theory [Larson, Odoni, ’81], [Gelenbe, Pujolle, Nelson, ‘98], [Osorio, Bierlaire, OR ’09]

Evaluation: Case Study of Singapore• Three complementary data sources: HITS survey, Singapore taxi data,

Singapore road network• 779,890 passenger vehicles operating in Singapore• 100 stations for robotic MoD

0 5 10 15 20 230

10

20

30

40

50

60

70

Time of day (hours)

Aver

age

wai

t tim

e (m

in)

200,000 vehicles250,000 vehicles300,000 vehicles

COS COT TMC

Traditional 0.96 0.76 1.72

AMoD 0.66 0.26 0.92

Mobility-related costs (USD/km)

[Spieser, Treleaven, Zhang, Frazzoli, Morton, Pavone, Road Vehicle Automation, ’14]

Key result: total mobility cost cut in half!

Conclusions1. Autonomous driving might lead to a transformational paradigm for personal

urban mobility (to improve or sustain current mobility needs)2. Integration of system-wide coordination and autonomous driving gives rise

to an entirely new class of problems at the interface of robotics and transportation research

3. Solutions to these problems are key to enable autonomous MoD and to carefully evaluate their value proposition

11

Future research directions:• Heterogeneity: multi-modal, smart grid, & society

Acknowledgements: NSF CAREER Award, Car2Go, Toyota, collaborators at Stanford (Ramon Iglesias, Federico Rossi, and Rick Zhang), MIT, and Singapore

Contact: pavone@stanford.edu

Charging demandEnergy storage

Electricity pricesEnergy provision

Power network

Transportation network