Accelerating Trajectory Generation for Quadrotors Using Transformers

被引:0
|
作者
Tankasala, Srinath [1 ]
Pryor, Mitch [1 ]
机构
[1] Univ Texas Austin, Cockrell Sch Engn, Austin, TX 78712 USA
关键词
Trajectory optimization; Minimum snap; Transformers;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this work, we address the problem of computation time for trajectory generation in quadrotors. Most trajectory generation methods for waypoint navigation of quadrotors, for example minimum snap/jerk and minimum-time, are structured as bi-level optimizations. The first level involves allocating time across all input waypoints and the second step is to minimize the snap/jerk of the trajectory under that time allocation. Such an optimization can be computationally expensive to solve. In our approach we treat trajectory generation as a supervised learning problem between a sequential set of inputs and outputs. We adapt a transformer model to learn the optimal time allocations for a given set of input waypoints, thus making it into a single step optimization. We demonstrate the performance of the transformer model by training it to predict the time allocations for a minimum snap trajectory generator. The trained transformer model is able to predict accurate time allocations with fewer data samples and smaller model size, compared to a feedforward network (FFN), demonstrating that it is able to model the sequential nature of the waypoint navigation problem.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Trajectory Generation for Quadrotors using Galerkin Projection and Fuzzy Inference
    Tian Yuan-yuan
    Wu Huni-Ning
    Feng Shuang
    PROCEEDINGS OF THE 35TH CHINESE CONTROL CONFERENCE 2016, 2016, : 5693 - 5698
  • [2] Minimum Snap Trajectory Generation and Control for Quadrotors
    Mellinger, Daniel
    Kumar, Vijay
    2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2011, : 2520 - 2525
  • [3] Decentralized polynomial trajectory generation for flight formation of quadrotors
    Sayyaadi, Hassan
    Soltani, Ali
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART K-JOURNAL OF MULTI-BODY DYNAMICS, 2017, 231 (04) : 690 - 707
  • [4] Trajectory generation and control for precise aggressive maneuvers with quadrotors
    Mellinger, Daniel
    Michael, Nathan
    Kumar, Vijay
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2012, 31 (05): : 664 - 674
  • [5] Optimal constrained trajectory generation for quadrotors through smoothing splines
    Lai, Shupeng
    Lan, Menglu
    Chen, Ben M.
    2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2018, : 4743 - 4750
  • [6] Novel Trajectory Generation and Adaptive Evolutionary Feedback Controller for Quadrotors
    Salamat, Babak
    Tonello, Andrea M.
    2018 IEEE AEROSPACE CONFERENCE, 2018,
  • [7] Minimum-Time Trajectory Generation for Quadrotors in Constrained Environments
    Spedicato, Sara
    Notarstefano, Giuseppe
    IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2018, 26 (04) : 1335 - 1344
  • [8] Online Safe Trajectory Generation For Quadrotors Using Fast Marching Method and Bernstein Basis Polynomial
    Gao, Fei
    Wu, William
    Lin, Yi
    Shen, Shaojie
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 344 - 351
  • [9] Decentralized MPC-Based Trajectory Generation for Multiple Quadrotors in Cluttered Environments
    Xinyi Wang
    Lele Xi
    Yizhou Chen
    Shupeng Lai
    Feng Lin
    Ben MChen
    Guidance,Navigation and Control, 2021, (02) : 44 - 63
  • [10] A Time-optimal Trajectory Generation Algorithm for Quadrotors with Various States Constraints
    He, Zhen
    Fang, Yongchun
    Liang, Xiao
    Lin, He
    Xiao, Yuting
    Zhang, Xuebo
    2018 3RD IEEE INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND MECHATRONICS (IEEE ICARM), 2018, : 880 - 885