Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Quick Multi-Agent Path Planning

Quick Multi-Agent Path Planning

Used in seminar talks in Cambridge, Newcastle, Brussels, etc., during August-September 2022

contents:
https://kei18.github.io/mapf-IR/ (IROS-21)
https://kei18.github.io/pibt2/ (IJCAI-19, AIJ-21)
https://kei18.github.io/lacam/ (AAAI-23)
https://omron-sinicx.github.io/ctrm/ (AAMAS-22)
https://kei18.github.io/sssp/ (IJCAI-23)

More Decks by Keisuke Okumura | 奥村圭祐

Other Decks in Research

Transcript

  1. 7th Sep. 2022
    at VUB Artificial Intelligence Lab
    Quick Multi-Agent Path Planning
    Keisuke Okumura
    Tokyo Institute of Technology, Japan
    ౦ژ޻ۀେֶ
    5PLZP*OTUJUVUFPG5FDIOPMPHZ

    View full-size slide

  2. /64
    2
    Ph.D. student at Tokyo Institute of Technology, Japan (Apr. 2020–)
    Advisor: Prof. Xavier DEFAGO
    Keisuke Okumura
    Research Interests Controlling Multiple Moving Agents
    AI & Robotics / Multi-Agent Planning / Multi-Robot Coordination
    https://kei18.github.io/
    visiting researcher at LIP6, Sorbonne Univ. (Mar. 2023–)
    Advisor: Prof. Sebastien TIXEUIL

    View full-size slide

  3. /64
    3
    YouTube/Mind Blowing Videos
    logistics
    YouTube/WIRED
    manufacturing
    YouTube/Tokyo 2020
    entertainment
    Swarm { is, will be } necessary
    in everywhere

    View full-size slide

  4. /64
    4
    objective-1
    Representation
    objective-2
    Planning
    Common Knowledge?
    Cooperation? (increased)
    Uncertainty
    Execution
    Navigation for a Team of Agents
    Who Plans?
    Huge Search Space

    View full-size slide

  5. /64
    TO
    DAY
    5
    representation
    planning
    execution
    integration
    domain-independent planning
    [preprint-22]
    [AAMAS-22]
    data-driven roadmap construction
    ≥1000 agents within 1 sec
    [IJCAI-19, IROS-21, ICAPS-22*, AIJ-22, …]
    [AAAI-21, ICRA-21, ICAPS-22*, IJCAI-22, …]
    async, (decentralized)
    *Best Student Paper Award
    How do we control multiple moving agents
    adaptively & smoothly?

    View full-size slide

  6. /64
    Outline
    multi-agent path planning in:
    continuous spaces
    CTRMs: data-driven approach [AAMAS-22]
    SSSP: domain-independent planning [preprint-22]
    discretized spaces
    PIBT: scalable & convenient algorithm [IJCAI-19 => AIJ-22]
    LaCAM: complete algorithm [unpublished yet]

    View full-size slide

  7. /64
    Outline
    multi-agent path planning in:
    continuous spaces
    CTRMs: data-driven approach [AAMAS-22]
    SSSP: domain-independent planning [preprint-22]
    discretized spaces
    PIBT: scalable & convenient algorithm [IJCAI-19 => AIJ-22]
    LaCAM: complete algorithm [unpublished yet]

    View full-size slide

  8. /64
    8
    MAPF: Multi-Agent Path Finding
    given agents (starts)
    graph
    goals
    solution paths without collisions
    optimization is intractable in various criteria
    [Yu+ AAAI-13, Ma+ AAAI-16, Banfi+ RA-L-17, Geft+ AAMAS-22]

    View full-size slide

  9. /64
    10
    Quality vs Speed
    with MAPF Benchmark
    [Stern+ SOCS-19]
    example; 194x194; |V|=13,214
    *limiting to popular methods
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    frontier line

    View full-size slide

  10. /64
    11
    Put Quality Aside
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    [Okumura+ IROS-21]
    iterative refinement
    for known solutions
    planning time (sec)
    cost / lower bond
    300 agents

    View full-size slide

  11. /64
    12
    Take Speed!
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    [Okumura+ IROS-21]
    iterative refinement
    developing
    quick & scalable
    sub-optimal methods

    View full-size slide

  12. /64
    13
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    PIBT
    [Okumura+ AIJ-22]
    my work!
    Take Speed!

    View full-size slide

  13. /64
    14
    planning
    online planning
    applicable to lifelong scenarios
    ≥500 agents within 50ms
    scalable sub-optimal algorithm (PIBT) to solve MAPF iteratively
    ensuring that all agents eventually reach their destinations
    https://kei18.github.io/pibt2
    IJCAI-19 => AIJ-22
    Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding
    KO, Manao Machida, Xavier Defago & Yasumasa Tamura

    View full-size slide

  14. /64
    15
    locations at t=1
    t=2
    t=3
    repeat one-timestep prioritized planning
    high low
    mid
    How PIBT works – 1/6

    1 2 3
    4 5 6
    7 8 9
    decision order
    time-window

    View full-size slide

  15. /64
    16
    How PIBT works – 2/6
    simple prioritized planning is incomplete
    high
    low
    mid stuck

    View full-size slide

  16. /64
    17
    How PIBT works – 3/6
    high
    low
    mid as high
    priority inheritance
    [Sha+ IEEE Trans Comput-90]

    View full-size slide

  17. /64
    18
    high low
    mid
    How PIBT works – 4/6
    1 3 2
    decision order
    … …

    View full-size slide

  18. /64
    19
    How PIBT works – 5/6
    high as high
    as high as high
    as high stuck
    but still not feasible

    View full-size slide

  19. /64
    20
    How PIBT works – 6/6
    invalid
    valid
    re-plan
    re-plan
    valid You can move
    invalid You must re-plan, I will stay
    introduce backtracking
    repeat this one-timestep planning until termination

    View full-size slide

  20. /64
    21
    Theoretical Result
    With dynamic priorities, in biconnected graphs,
    all agents reach their destinations within finite timestep
    convenient in lifelong scenarios
    important note:
    PIBT is incomplete for MAPF
    unsolvable,
    but the theorem is valid

    View full-size slide

  21. /64
    22
    Multi-agent Pickup & Delivery
    Sushi
    Sushi plates are ensured to be delivered

    View full-size slide

  22. /64
    23
    prioritized planning
    w/distance-based heuristics [Silver AIIDE-05]
    A* with operator decomposition
    greedy version [Standley AAAI-10]
    EECBS
    CBS-based, bounded sub-optimal [Li+ AAAI-21]
    LNS2
    large neighborhood search for MAPF [Li+ AAAI-22]
    PIBT
    Performance on
    one-shot MAPF
    25 instances
    30sec timeout on desktop PC
    sufficiently long timestep limit
    194x194 four-connected grid
    sum-of-costs
    (normalized; min:1)
    50 250 500 750 1000
    1.0
    1.2
    1.4
    1.6
    1.8
    runtime
    (sec)
    50 250 500 750 1000
    0
    10
    20
    30
    success rate
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    agents
    not so bad
    not so bad
    blazing fast!
    worst: 550ms

    View full-size slide

  23. /64
    24
    PIBT is great but…
    agents
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    room-64-64-8
    64x64
    |V|=3,232
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    ost003d
    194x194
    |V|=13,214
    agents
    50 100 200 300 400
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    random-32-32-20
    32x32
    |V|=819
    agents
    important note:
    PIBT is incomplete for MAPF
    We need one more jump!
    PIBT 0%
    success rate
    in 30sec

    View full-size slide

  24. /64
    25
    planning
    LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding
    KO (under review)
    agents
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    room-64-64-8
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    ost003d
    agents
    50 100 200 300 400
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    random-32-32-20
    agents
    success rate
    in 30sec
    100%
    LaCAM
    worst: 699ms worst: 394ms worst: 11sec
    quick & complete algorithm for MAPF (LaCAM; lazy constraints addition search)

    View full-size slide

  25. /64
    26

    … …
    … …
    search node
    (configuration)
    Vanilla A* for MAPF
    greedy search: 44 nodes
    in general: (5^N)xT nodes
    N: agents, T: depth
    intractable even with
    perfect heuristics
    goal configuration

    View full-size slide

  26. /64
    27
    PIBT for MAPF
    PIBT
    PIBT
    PIBT
    greedy search: 44 nodes
    only 4 configurations
    repeat one-timestep planning until termination
    use PIBT to guide exhaustive search
    initial configuration
    goal configuration

    View full-size slide

  27. /64
    28

    … …
    … …
    Concept of LaCAM
    PIBT
    PIBT
    PIBT
    the algorithm is beautiful but complicated
    use other MAPF algorihtms
    to generate a promising configuration
    configurations are generated
    in a lazy manner
    by two-level search scheme
    exhaustive search but node
    generation are dramatically reduced
    => quick & complete MAPF

    View full-size slide

  28. /64
    29
    sum-of-costs
    (normalized; min:1)
    50 250 500 750 1000
    1.0
    1.2
    1.4
    1.6
    1.8
    runtime
    (sec)
    50 250 500 750 1000
    0
    10
    20
    30
    success rate
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    agents
    prioritized planning
    w/distance-based heuristics [Silver AIIDE-05]
    A* with operator decomposition
    greedy version [Standley AAAI-10]
    EECBS
    CBS-based, bounded sub-optimal [Li+ AAAI-21]
    LNS2
    large neighborhood search for MAPF [Li+ AAAI-22]
    PIBT
    [Okumura+ AIJ-22]
    Performance on
    one-shot MAPF
    25 instances, on laptop
    30sec timeout
    sufficiently long timestep limit
    194x194 four-connected grid
    not so bad
    LaCAM
    blazing fast!
    worst: 699ms
    perfect!

    View full-size slide

  29. /64
    30
    2 4 6 8 10
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    success rate
    in 1000sec
    2 4 6 8 10
    101
    102
    103
    runtime
    (sec)
    agents (x1000)
    25 instances, timeout of1000 sec, on desctop PC
    warehouse-20-40-10-2-2, 340x164; |V|=38,756
    Performance with
    x1000 agents
    perfect!
    blazing fast!
    worst: 26sec
    for 10,000 agents
    LaCAM
    wrong thought:
    “centralized algorithms are not scalable”
    => NO, the game is changing
    PIBT
    demo of 10,000 agents

    View full-size slide

  30. /64
    31
    LaCAM is great but…
    My research will continue
    agents
    50 100 200 300
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    maze-32-32-2
    32x32
    |V|=666
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    lt_gallowstemplar_n
    251x180
    |V|=10,021
    agents
    50 250 500 750 1000
    0.0
    0.2
    0.4
    0.6
    0.8
    1.0
    warehouse-20-40-10-2-1
    321x123
    |V|=22,599
    agents
    0%
    success rate
    in 30sec
    narrow corridors
    can be bottleneck
    LaCAM

    View full-size slide

  31. /64
    32
    Take Speed!
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    developing
    quick & scalable
    sub-optimal methods
    [Okumura+ IROS-21]
    iterative refinement

    View full-size slide

  32. /64
    33
    Take Speed!
    solution quality
    optimal
    ≥1000 agents in seconds
    speed & scalability
    ~100 agents in minutes
    Push & Swap/Rotate
    [Luna+ IJCAI-11, de Wilde+ AAMAS-13]
    EECBS [Li+ AAAI-21]
    HCA* [Silver AIIDE-05]
    BCP [Lam+ COR-22]
    CBS [Sharon+ AIJ-15, Li+ AIJ-21]
    [Okumura+ IROS-21]
    iterative refinement
    LaCAM
    PIBT [Okumura+ AIJ-22]

    View full-size slide

  33. /64
    Outline
    multi-agent path planning in:
    continuous spaces
    CTRMs: data-driven approach [AAMAS-22]
    SSSP: domain-independent planning [preprint-22]
    discretized spaces
    PIBT: scalable & convenient algorithm [IJCAI-19 => AIJ-22]
    LaCAM: complete algorithm [unpublished yet]

    View full-size slide

  34. /64
    35
    MAPF definition again
    given agents (starts)
    graph
    goals
    solution paths without collisions
    reality is continuous

    View full-size slide

  35. /64
    36
    Cool coordination but not efficient!
    why not move diagonally?
    robots follow grid
    [Okumura+ ICAPS-22]

    View full-size slide

  36. /64
    37
    Multi-Agent Path Planning in Continuous Spaces
    given agents (starts)
    goals
    solution paths without collisions
    finding solutions itself is tremendously challenging
    [Spirakis+ 84, Hopcroft+ IJRR, Hearn+ TCS-05]
    workspace

    View full-size slide

  37. /64
    38
    artificial potential field sampling-based
    rule-based
    goal
    start
    Strategies to Solve
    Single-Agent Path Planning
    in Continuous Spaces
    constructing
    roadmap

    View full-size slide

  38. /64
    39
    SBMP: Sampling-Based Motion Planning
    state of robot: (x, y)
    (x, y) should be
    in this region
    configuration space
    random sampling &
    construct roadmap
    pathfinding on
    roadmap
    same scheme even in high-dimension

    View full-size slide

  39. /64
    40
    Naïve Strategy to Solve
    Multi-Agent Path Planning
    in Continuous Spaces
    Construct agent-wise roadmaps
    by SBMP (sampling-based motion planning) methods
    1.
    Solve MAPF on those roadmaps
    2.

    View full-size slide

  40. /64
    41
    produced by PRM [Kavraki+ 96]
    Pitfall – There is a trade-off
    dense sparse
    large small
    planning effort
    high low
    solution quality
    big impact in multi-agent scenarios
    ideal: small roadmaps containing high-quality solutions

    View full-size slide

  41. /64
    42
    Countermeasure
    biased sampling
    sampling from important region of each agent
    how to identify?
    agent-specific features +
    interactions between agents
    !
    design manually?

    View full-size slide

  42. /64
    43
    Countermeasure
    biased sampling
    sampling from important region of each agent
    how to identify?
    agent-specific features +
    interactions between agents
    This is machine learning problem!
    supervised learning: planning demonstration as training data

    View full-size slide

  43. /64
    44
    representation
    CTRMs: Learning to Construct Cooperative Timed Roadmaps
    for Multi-agent Path Planning in Continuous Spaces
    KO,* Ryo Yonetani, Mai Nishimura & Asako Kanezaki
    https://omron-sinicx.github.io/ctrm
    AAMAS-22
    *work done as an intern at OMRON SINIC X
    data-driven roadmap construction, reducing planning effort significantly
    constructed roadmaps
    MAPF algorithm
    solution

    View full-size slide

  44. /64
    45
    !!"#$
    model training
    instances & solutions predict next locations
    MAPF
    algorithm
    new instance
    !!"#$
    random
    walk
    sampling module
    next
    locations
    for all agents
    starts
    path generation
    compositing
    solution

    t=0 t=1 t=2
    CTRMs
    Workflow
    Online Inference
    Offline Training
    CVAE: Conditional Variational Autoencoder
    [Sohn+ NeurIPS-15]
    +importance sampling
    [Salzmann+ ECCV-20]
    +multi-agent attention
    [Hoshen NeurIPS-17]
    !"#$%
    :

    View full-size slide

  45. /64
    !"#$%
    46
    next position
    instance & solution
    occupancy
    cost-to-go
    env.
    info
    Offline Training & Model Arch.
    [Sohn+ NeurIPS-15]
    CVAE
    features
    ?

    View full-size slide

  46. /64
    !"#$%
    47
    +
    +
    goal-driven
    features
    relative positions,
    size, speeds, etc
    Offline Training & Model Arch.

    View full-size slide

  47. /64
    !"#$%
    48
    +
    +
    comm.
    features
    attention
    Offline Training & Model Arch.
    [Hoshen NeurIPS-17]

    View full-size slide

  48. /64
    !"#$%
    49
    go right
    [0,0,1]
    indicator
    feature
    Offline Training & Model Arch.

    View full-size slide

  49. /64
    !"#$%
    50
    +
    +
    +
    +
    go right
    [0,0,1]
    next position
    goal-driven
    features
    comm.
    features
    indicator
    feature
    instance & solution
    occupancy
    cost-to-go
    env.
    info
    relative positions,
    size, speeds, etc
    attention
    Offline Training & Model Arch.
    [Sohn+ NeurIPS-15]
    CVAE
    [Hoshen NeurIPS-17]

    View full-size slide

  50. /64
    51
    observations
    for agent-i
    next predicted location
    for agent-i
    trained model
    likely to be used by planners
    Online Inference

    View full-size slide

  51. /64
    52
    Online Inference
    timestep t timestep t+1
    next predicted locations
    for all agents
    observations
    for all agents

    View full-size slide

  52. /64
    53
    Online Inference
    t=0 t=1 t=2 t=T
    t=T-1

    initial locations
    timed path for agent-i
    each path is agent-specific and cooperative
    hyperparameter

    View full-size slide

  53. /64
    54




    compositing
    t=0 t=1 t=2 t=T
    t=T-1
    timed roadmap for agent-i
    each roadmap is agent-specific and cooperative
    hyperparameter:
    #(path generation)
    Online Inference

    View full-size slide

  54. /64
    55
    SPARS
    [Dobson & Bekris, IJRR-14]
    (random)
    simplified PRM
    [Karaman & Frazzoli, IJRR-11]
    square
    as agent-specific roadmaps
    grid
    as used in MAPF studies
    CTRMs
    20-30 homo agents
    corresponding to 32x32 grids
    CTRMs produce small but effective roadmaps specific to each agent
    Roadmap Visualization

    View full-size slide

  55. /64
    56
    Quantitative Results
    103 104 105
    exSanded nRdes / agents
    0
    10
    20
    30
    40
    suP-Rf-cRsts / agents
    average Rver 40/100 instances
    CT50s
    randRP
    grid
    S3A5S
    sTuare
    20-30 homo agents
    corresponding to 32x32 grids
    100 instances
    solved by prioritized planning
    [Silver, AIIDE-05, Van Den Berg &
    Overmars IROS-05, etc]
    CTRMs reduce planning effort
    while keeping solution qualities
    params of CTRMs:
    #(path generations)
    sparse
    dense

    View full-size slide

  56. /64
    57
    CT50
    s
    randRP
    grid
    S3A5S
    sTuare
    0
    100
    200
    300
    400
    500
    runtiPe (sec)
    x
    average Rver 40/100 instances
    rRadPaS
    Slanner
    20-30 homo agents
    corresponding to 32x32 grids
    100 instances
    solved by prioritized planning
    [Silver, AIIDE-05, Van Den Berg &
    Overmars IROS-05, etc]
    CTRMs achieve efficient path-planning
    from the end-to-end perspective
    sparse dense
    Roadmap construction can be much faster.
    Check our latest implementation:
    https://github.com/omron-sinicx/jaxmapp
    Quantitative Results
    quick!

    View full-size slide

  57. /64
    58
    representation of environment is critical for planning
    develop agent-wise roadmaps
    according to multi-agent search progress

    View full-size slide

  58. /64
    59
    Quick Multi-Robot Motion Planning by Combining Sampling & Search
    KO & Xavier Defago (under review)
    planning representation
    algorithm (SSSP) to solve multi-robot motion planning quickly
    simultaneously perform roadmap construction & collision-free pathfinding
    https://kei18.github.io/sssp
    32 robots

    View full-size slide

  59. /64
    60
    MRMP: Multi-Robot Motion Planning
    MAPF is a special case of MRMP
    Solution: collision-free trajectorie
    Each agent has its own configuration space
    To make MRPP domain-independent, only five utility functions are available
    sample collide
    steer
    dist
    connect
    free space
    true
    false
    true
    false
    0.18

    View full-size slide

  60. /64
    61
    Proposed Algorithm: SSSP
    search progress solution
    MAPF
    A* with operator decomposition
    [Standley AAAI-10]
    SBMP
    EST: expansive space trees
    [Hsu+ ICRA-97]
    integration
    +many tricks inspired by SBMP & MAPF studies
    exhaustive search like vanilla A* while constructing roadmaps through random walks

    View full-size slide

  61. /64
    62
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    RRT
    RRT-C
    PP
    CBS
    SSSP
    Point2d
    DOF: 2N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    RRT
    RRT-C
    PP
    CBS
    SSSP
    Point3d
    DOF: 3N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    RRT-C
    RRT
    CBS
    PP
    SSSP
    Line2d
    DOF: 3N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    RRT
    PP
    CBS
    RRT-C
    SSSP
    Capsule3d
    DOF: 6N
    0 200 400 600 800 1000
    olved in tance
    0
    100
    200
    300
    runtime ( ec)
    PRM
    PP/CBS
    RRT-C
    RRT
    SSSP
    Arm22
    DOF: 2N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    PP
    CBS
    RRT
    RRT-C
    SSSP
    Arm33
    DOF: 6N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    PRM
    RRT
    RRT-C
    PP
    CBS
    SSSP
    Dubins2d
    DOF: 3N
    0 200 400 600 800 1000
    solved ins ances
    0
    100
    200
    300
    run ime (sec)
    RRT-C
    CBS
    PP/RRT
    SSSP
    Snake2d
    DOF: 6N
    Performance of SSSP
    very promising
    quick!

    View full-size slide

  62. /64
    63
    ML
    Machine Learning as Heuristics
    integration
    SBMP
    Sampling-Based
    Motion Planning
    MAPF
    Multi-Agent
    Path Finding
    My Future Research?
    establish practical methodologies to MRMP

    View full-size slide

  63. /64
    64
    Takeaways
    difficult, but will be possible
    Quick Multi-Agent Path Planning
    still being hot in the next decade, e.g., MRMP is not matured at all

    View full-size slide

  64. /64
    More Info? => Check My Website!
    https://kei18.github.io/
    Thank You for Listening!
    Collaboration is welcome!

    View full-size slide