This paper presents a traversability assessment method and a trajectory planning method. They are key features for the navigation of an unmanned ground vehicle (UGV) in a non-planar environment. In this work, a 3D light detection and ranging (LiDAR) sensor is used to obtain the geometric information about a rough terrain surface. For a given SE(2) pose of the vehicle and a specific vehicle model, the SE(3) pose of the vehicle is estimated based on LiDAR points, and then a traversability is computed. The traversability tells the vehicle the effects of its interaction with the rough terrain. Note that the traversability is computed on demand during trajectory planning, so there is not any explicit terrain discretization. The proposed trajectory planner finds an initial path through the non-holonomic A*, which is a modified form of the conventional A* planner. A path is a sequence of poses without timestamps. Then, the initial path is optimized in terms of the traversability, using the method of Lagrange multipliers. The optimization accounts for the model of the vehicle’s suspension system. Therefore, the optimized trajectory is dynamically feasible, and the trajectory tracking error is small. The proposed methods were tested in both the simulation and the real-world experiments. The simulation experiments were conducted in a simulator called Gazebo, which uses a physics engine to compute the vehicle motion. The experiments were conducted in various non-planar experiments. The results indicate that the proposed methods could accurately estimate the SE(3) pose of the vehicle. Besides, the trajectory cost of the proposed planner was lower than the trajectory costs of other state-of-the-art trajectory planners.
1 March 2020 in International Journal of Advanced Robotic Systems
This article introduces a continuous reinforcement learning framework to enable online adaptation of multi-objective optimization functions for guiding a mobile robot to move in changing dynamic environments. The robot with this framework can continuously learn from multiple or changing environments where it encounters different numbers of obstacles moving in unknown ways at different times. Using both planned trajectories from a real-time motion planner and already executed trajectories as feedback observations, our reinforcement learning agent enables the robot to adapt motion behaviors to environmental changes. The agent contains a Q network connected to a long short-term memory network. The proposed framework is tested in both simulations and real robot experiments over various, dynamically varied task environments. The results show the efficacy of online continuous reinforcement learning for quick adaption to different, unknown, and dynamic environments.
13 January 2016 in Journal of Signal Processing Systems
This paper presents a search-based global motion planning method, called the two-phase A*, with an adaptive heuristic weight. This method is suitable for planning a global path in real time for a car-like vehicle in both indoor and outdoor environments. In each planning cycle, the method first estimates a proper heuristic weight based on the hardness of the planning query. Then, it finds a nearly optimal path subject to the non-holonomic constraints using an improved A* with a weighted heuristic function. By estimating the heuristic weight dynamically, the two-phase A* is able to adjust the optimality level of its path based on the hardness of the planning query. Therefore, the two-phase A* sacrifices little planning optimality, and its computation time is acceptable in most situations. The two-phase A* has been implemented and tested in the simulations and real-world experiments over various task environments. The results show that the two-phase A* can generate a nearly optimal global path dynamically, which satisfies the non-holonomic constraints of a car-like vehicle and reduces the total navigation time.
Robot path planning is a hot issue in the robotics field. Based on many algorithms, we consider the efficiency and accuracy of path planning. This paper proposes a path planning method that combines improved ant colony algorithm and $\mathrm{A}^{\ast}$ algorithm. First, by improving the pheromone update method, state transition probability and heuristic function in the ant colony algorithm, an ant colony algorithm with better performance is obtained. Afterwards, aiming at the defect that the same initial pheromone concentration in the ant colony algorithm leads to the purposeless search of the first-generation ant colony, the fusion improved ant colony algorithm and the $\mathrm{A}^{\ast}$ algorithm are proposed, and simulation experiments are carried out. The experimental results show that the path is planned through the fusion algorithm the search time is shortened, the number of iterations when reaching convergence is reduced, and a better path can be obtained, which shows that the algorithm can achieve good results when dealing with path planning problems.