scholarly journals AlphaPilot: autonomous drone racing

2021 ◽  
Author(s):  
Philipp Foehn ◽  
Dario Brescianini ◽  
Elia Kaufmann ◽  
Titus Cieslewski ◽  
Mathias Gehrig ◽  
...  
Keyword(s):  
Real Time ◽  
Trajectory Planning ◽  
Nonlinear Filtering ◽  
Optimal Trajectory ◽  
Optimal Path ◽  
Data Abstraction ◽  
State Estimate ◽  
World Championship ◽  
Time Optimal ◽  
Optimal Trajectory Planning

AbstractThis paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The system has successfully been deployed at the first autonomous drone racing world championship: the 2019 AlphaPilot Challenge. Contrary to traditional drone racing systems, which only detect the next gate, our approach makes use of any visible gate and takes advantage of multiple, simultaneous gate detections to compensate for drift in the state estimate and build a global map of the gates. The global map and drift-compensated state estimate allow the drone to navigate through the race course even when the gates are not immediately visible and further enable to plan a near time-optimal path through the race course in real time based on approximate drone dynamics. The proposed system has been demonstrated to successfully guide the drone through tight race courses reaching speeds up to $${8}\,{\hbox {m}/\hbox {s}}$$ 8 m / s and ranked second at the 2019 AlphaPilot Challenge.

Time Optimal Path Planning of Palletizing Robot

2013 ◽  
Vol 470 ◽  
pp. 658-662
Author(s):  
Yong Pan Xu ◽  
Ying Hong
Keyword(s):  
Trajectory Planning ◽  
Optimal Trajectory ◽  
Optimal Path ◽  
Straight Path ◽  
Optimal Path Planning ◽  
Quintic Polynomial ◽  
Time Optimal ◽  
Acceleration And Deceleration ◽  
Planning Algorithm ◽  
Optimal Trajectory Planning

In order to improve the efficiency and reduce the vibration of Palletizing Robot, a new optimal trajectory planning algorithm is proposed. This algorithm is applied to the trajectory planning of Palletizing manipulators. The S-shape acceleration and deceleration curve is adopted to interpolate joint position sequences. Considering constraints of joint velocities, accelerations and jerks, the traveling time of the manipulator is minimized. The joint interpolation confined by deviation is used to approximate the straight path, and the deviation is decreased significantly by adding only small number of knots. Traveling time is solved by using quintic polynomial programming strategy between the knots, and then time-jerk optimal trajectories which satisfy constraints are planned. The results show that the method can avoid the problem of manipulator singular points and improve the palletize efficiency.

A Novel Algorithm for Time Optimal Trajectory Planning

2014 ◽  
Author(s):  
Mingxing Yuan ◽  
Bin Yao ◽  
Dedong Gao ◽  
Xiaocong Zhu ◽  
Qingfeng Wang
Keyword(s):  
Trajectory Planning ◽  
Optimal Trajectory ◽  
Optimal Solution ◽  
Problem Of Time ◽  
High Productivity ◽  
Hard Constraints ◽  
Time Optimal ◽  
Rate Optimization ◽  
Feed Rate Optimization ◽  
Optimal Trajectory Planning

Time optimal trajectory planning under various hard constraints plays a significant role in simultaneously meeting the requirements on high productivity and high accuracy in the fields of both machining tools and robotics. In this paper, the problem of time optimal trajectory planning is first formulated. A novel back and forward check algorithm is subsequently proposed to solve the minimum time feed-rate optimization problem. The basic idea of the algorithm is to search the feasible solution in the specified interval using the back or forward operations. Four lemmas are presented to illustrate the calculating procedure of optimal solution and the feasibility of the proposed algorithm. Both the elliptic curve and eight profile are used as case studies to verify the effectiveness of the proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document