Generalized Predictive Planning for Autonomous Vehicles Scott Pendleton and Marcelo H. Ang Jr. Department of Mechanical Engineering National University of Singapore 2017/9/24 1
Why Autonomous Vehicles? (Singapore Perspectives) • Reduce car ownership – Ride sharing, delivery, logistics • Efficient use of resources – Car, road infrastructure, less parking spaces • Public transportation – Last mile/first mile problem – Urban driving as opposed to highways • Improved Productivity & Safety, “greener” 2
INTRODUCTION & MOTIVATION Autonomous Mobility ‐ on ‐ Demand • Vehicle sharing for first-and-last-mile transportation Availability Accessibility Affordability Ride Sharing Autonomy • Multiple vehicle classes: Operational advantages for each vehicle class favor different environments. A combined multi-class service can extend the operational area. True point-to-point service coverage is achievable. • Disruptive technology: Automation can enable new ways of thinking about automobiles and transportation systems in general. In particular, it can provide affordable, convenient, on-demand mobility. 3
Environments • Road • Pedestrian 4
SMART=NUS Fleet 5
What we can confidently do? • Reactive control with guaranteed safety (lowest layer – always on) • Mapping and Localization • Local planning – RRT* variant – POMDP • Execution & Control – More accurate path following using kinematic constraints 6
Mobility on Demand using Multi ‐ Class Autonomous Vehicles 7
• One North: – Jan 2015 – 6 km route – Sept 2016 – 12 km route – 23 June 2017 – 55 km ‐ NUS & Science Pk • 9 vehicles – SMART-NUS: 1 – Nutonomy: 6 – Delphi : 1 – A*STAR: 1 8 8
One North – Live Testing 9
One North – May 2017 Pedestrian crossing Signalized Intersection Complex intersection Road construction Road construction and jay walking 10
Public Deployment at the Chinese & Japanese Gardens (Oct 2014) ‐ Long Term Vehicle Testing ‐ To raise awareness ‐ To gain public acceptance 6 Days 360 km 500 Visitors 220 Trips 225 Surveys 98% “would ride again” 11
12
our autonomous mobility scooter 13
PREDICTIVE PLANNING FRAMEWORK Our Planning Framework • Interface planning modules with perception and control modules • Incorporate acceleration constraints • Establish replanning timing/retriggering • Safety mechanism design for predictive planning 14
PREDICTIVE PLANNING FRAMEWORK Planning Framework Overview 15
PREDICTIVE PLANNING FRAMEWORK Planning Framework Overview • Booking System & Mission Planner • Mobile phone access to webserver for handling mission requests as {Pickup Station, Dropoff Station} • Dijkstra search over directed graph of reference path segments • Mapping/Localization • Vertical features extracted from 3D point cloud gathered from 2D LIDAR “rolling window” accumulation over time • Obstacle Detection • SVM performed over spatio ‐ temporal features of object clusters from 2D LIDAR 16
PREDICTIVE PLANNING FRAMEWORK Planning Framework Overview • Cost Map Generator • Obstacle avoidance cost set for grid locations in a 3D cost map layered by time dimension, up to a time horizon • Goal Generator • Goal state set at constant distance ahead along route plan • Steering Control • Pure ‐ pursuit steering find constant radius arc target to forward waypoint • Speed Control • Proportional Integral (PI) controller with switching mechanism for throttle vs. braking 17
PREDICTIVE PLANNING FRAMEWORK Trajectory Planner • Control and Path Guided RRT* (CPG ‐ RRT*) – Use RG, path guided sample biasing, and min ‐ jerk edge connection • Same structure of RRT*, but redefine subfunctions: – “Nearest” is RG NN search – “SampleFree” uses biasing – “Line” uses an min ‐ jerk profile interpolation along Dubins car paths – “Steer” and “CollisionFree” are built off the “Line” function 18
PREDICTIVE PLANNING FRAMEWORK Trajectory Planner: SampleFree • Retain previous iteration knowledge by Φ i ‐ 1 • Bias toward route plan by Φ pp • SampleGoal for greedy search • RG Sample for efficient exploration 19
PREDICTIVE PLANNING FRAMEWORK Trajectory Planner: Line • Controllable trajectory generation to enforce: – Minimum turning radius (Dubins curves) – Velocity bounds – Acceleration bounds • Edges are min ‐ jerk optimal for comfort – Minimizes – Known to be 5 th degree polynomial for position • Trajectory defined over Dubins x Velocity x Time – Configuration space 20
PREDICTIVE PLANNING FRAMEWORK Trajectory Planner: Line • First, solve for Dubins curve in SE(2) space • Then, solve for position, velocity, and acceleration w.r.t time by system of equations for boundary conditions: • Known: p init , v init , a init , p final , v final . set a final = 0 • Solve for constants b 0 … b 5 21
PREDICTIVE PLANNING FRAMEWORK Trajectory Planner: Line • Polynomial solutions found quickly • Bounds checked over time interval at endpoints and roots 22
PREDICTIVE PLANNING FRAMEWORK Replan Timing • Each plans is generated while previous plan is executed 23
PREDICTIVE PLANNING FRAMEWORK Safety Checking • Each solution plan is rechecked against an updated observation before execution • A new variant of braking Inevitable Collision State (ICS b ) is applied for passive safety: – A braking maneuver must exist from the commit state following the solution trajectory to satisfy dynamic minimum braking distance – Otherwise, velocity profile of solution is overridden by constant deceleration profile up to braking distance • “Clear zone” applied to command stop when obstacles are very close 24
PREDICTIVE PLANNING FRAMEWORK Control Interfacing • Planner must know next commit state as root for plan tree – Control and/or localization error may affect true pose – s 1 is expected commit state at end of trajectory Φ 0 , but instead arrive at s 1 ’ – Where to begin plan Φ 2 ? Introduce pose correction factor! – Start plan Φ 2 from state s 2 + w Δ s 1 (we use w = 0.5) 25
PREDICTIVE PLANNING FRAMEWORK Control Interfacing • Pose correction in practice: – Red is odometry trace (series of vectors) – Yellow is commit path – Overlap correlates with velocity undershoot, gap for overshoot 26
PREDICTIVE PLANNING FRAMEWORK Summary: Planning Framework • Predictive planning framework – Real ‐ time replanning in space ‐ time • Trajectory planning algorithm (CPG ‐ RRT*) – Generates min ‐ jerk controllable edge connections – Biased sampling for • Near previous solution trajectory • Near pure pursuit steering trajectory to route plan • Near goal • Reachable configuration space • Passive safety assurances through adapted braking Inevitable Collison State Avoidance (ICS b ) 27
VEHICLE PLATFORM DEVELOPMENT Software Overview Booking App Fleet Management System Server Users Onboard Verification Multi-Class Autonomous Vehicles 28
VEHICLE PLATFORM DEVELOPMENT Software Overview 29
VEHICLE PLATFORM DEVELOPMENT Hardware Overview • Common Sensor Suite • IMU & wheel encoders for odometry • 1 2D LIDAR for Mapping & Localization (M&L) – fuse w/odom • ≥ 1 2D LIDAR for Obstacle Detection (OD) • Similar Power Management & Off ‐ the ‐ shelf Computers • Ubuntu 14.04, ROS Indigo, i7 processor, 16GB RAM, SSD • Differing Actuation Mechanisms to Control: • Steering • Braking/Throttle • Gear Selection (Forward/Reverse) 30
VEHICLE PLATFORM DEVELOPMENT Hardware Overview Start with a personal mobility scooter, then add… 31
VEHICLE PLATFORM DEVELOPMENT Hardware Overview Start with a golf car, then add… 32
VEHICLE PLATFORM DEVELOPMENT Hardware Overview Start with a road car, then add… 33
VEHICLE PLATFORM DEVELOPMENT Safety Overrides • User Button Controls: • Pause • Auto • Manual • E ‐ stops, onboard and remote • Visualizations onboard show perception data and planned path • Audio cues for station arrival/departure 34
VEHICLE PLATFORM DEVELOPMENT Experiment Setup • Look for positive emergent behaviors • Compare against baseline planning method: • Decoupled spatial path and velocity planning • Enlarge obstacle bounds forward based on velocity to treat environment as static • Trigger replanning only when at a stop due to blockage • Test Scenarios: • Pedestrian navigation • T ‐ junction • Defensive driving • Overtaking 35
VEHICLE PLATFORM DEVELOPMENT Experiment Setup • Planning visualization 36
EXPERIMENTAL VALIDATION Predictive Planning Video • Video available on YouTube: search “FMAutonomy” channel https://youtu.be/eVVGZxp03Hc 37
What have we achieved? • Reactive Control – Guaranteed Safety as a Baseline • Generalize predictive planning – Plans coupled spatial path and velocity – Demonstrated over varied vehicle types and environments in high ‐ risk scenarios • Reachability Guidance – Speed improvement by factor of 9 ‐ 10 • Predictive Planning Framework – CPG ‐ RRT* (biased sampling and min ‐ jerk edges) – Modified ICS b passive safety assurances 38
Recommend
More recommend
