More Like this

1. CLF-CBF Constraints for Real-Time Avoidance of Multiple Obstacles in Bipedal Locomotion and Navigation

   https://doi.org/10.1109/IROS55552.2023.10341626  

   Liu, Jinze; Li, Minzhe; Grizzle, Jessy W; Huang, Jiunn-Kai (October 2023, IEEE)

   IEEE (Ed.)

   This paper presents a reactive planning system that allows a Cassie-series bipedal robot to avoid multiple non-overlapping obstacles via a single, continuously differentiable control barrier function (CBF). The overall system detects an individual obstacle via a height map derived from a LiDAR point cloud and computes an elliptical outer approximation, which is then turned into a CBF. The QP-CLF-CBF formalism developed by Ames et al. is applied to ensure that safe trajectories are generated. Safe planning in environments with multiple obstacles is demonstrated both in simulation and experimentally on the Cassie biped. 

   more » « less
2. Efficient Robot Motion Planning via Sampling and Optimization

   https://doi.org/10.23919/ACC50511.2021.9483146  

   Leu, Jessica; Zhang, Ge; Sun, Liting; Tomizuka, Masayoshi (May 2021, 2021 American Control Conference (ACC))

   null (Ed.)

   Robot motion planning is one of the important elements in robotics. In environments full of obstacles, it is always challenging to find a collision-free and dynamically feasible path between the robot's initial configuration and goal configuration. While many motion planning algorithms have been proposed in the past, each of them has its pros and cons. This work presents a benchmark which implements and compares existing planning algorithms on a variety of problems with extensive simulation. Based on that, we also propose a hybrid planning algorithm, RRT*-CFS, that combines the merits of sampling-based planning methods and optimization-based planning methods. The first layer, RRT*, quickly samples a semi-optimal path. The second layer, CFS, performs sequential convex optimization given the reference path from RRT*. The proposed RRT*-CFS has feasibility and convergence guarantees. Simulation results show that RRT*-CFS benefits from the hybrid structure and performs robustly in various scenarios including the narrow passage problems. 

   more » « less
3. Spatio-temporal Motion Planning for Autonomous Vehicles with Trapezoidal Prism Corridors and Bézier Curves

   https://doi.org/10.23919/ACC55779.2023.10155930  

   Deolasee, S.; Lin, Q.; Li, J.; Dolan, J.M. (May 2023, Proceedings of the American Control Conference)

   Safety-guaranteed motion planning is critical for self-driving cars to generate collision-free trajectories. A layered motion planning approach with decoupled path and speed planning is widely used for this purpose. This approach is prone to be suboptimal in the presence of dynamic obstacles. Spatial-temporal approaches deal with path planning and speed planning simultaneously; however, the existing methods only support simple-shaped corridors like cuboids, which restrict the search space for optimization in complex scenarios. We propose to use trapezoidal prism-shaped corridors for optimization, which significantly enlarges the solution space compared to the existing cuboidal corridors-based method. Finally, a piecewise Bezier curve optimization is conducted in our proposed ´ corridors. This formulation theoretically guarantees the safety of the continuous-time trajectory. We validate the efficiency and effectiveness of the proposed approach in numerical and CommonRoad simulations 

   more » « less
4. Multi-Objective Safe-Interval Path Planning with Dynamic Obstacles

   https://doi.org/10.1109/LRA.2022.3187270  

   Ren, Zhongqiang; Rathinam, Sivakumar; Likhachev, Maxim; Choset, Howie (January 2022, IEEE robotics automation letters)

   NA (Ed.)

   Path planning among dynamic obstacles is a fundamental problem in Robotics with numerous applications. In this work, we investigate a problem called Multi-Objective Path Planning with Dynamic Obstacles (MOPPwDO), which requires finding collision-free Pareto-optimal paths amid obstacles moving along known trajectories while simultaneously optimizing multiple conflicting objectives, such as arrival time, communication robustness and obstacle clearance. Most of the existing multiobjective A*-like planners consider no dynamic obstacles, and naively applying them to address MOPPwDO can lead to large computation times. On the other hand, efficient algorithms such as Safe-Interval Path Planing (SIPP) can handle dynamic obstacles but for a single objective. In this work, we develop an algorithm called MO-SIPP by leveraging both the notion of safe intervals from SIPP to efficiently represent the search space in the presence of dynamic obstacles, and search techniques from multiobjective A* algorithms. We show that MO-SIPP is guaranteed to find the entire Pareto-optimal front, and verify MO-SIPP with extensive numerical tests with two and three objectives. The results show that the MO-SIPP runs up to an order of magnitude faster than the conventional alternates. I 

   more » « less
5. LEAP-O: Learning to Predict Dynamic Obstacles for Safe Trajectory Planning

   Nguyen, Binh; Nghiem, Truong X; Nguyen, Linh; La, Hung; Nguyen, Thang (May 2026, IEEE)

   Trajectory planning plays a crucial role in autonomous driving and navigation by enabling robots to generate safe paths while minimizing travel costs and avoiding collisions. This paper addresses the issue of predicting dynamic obstacles for safe trajectory planning when prior information is unavailable and detection range is limited. We propose a learning framework using Gaussian Processes (GP) for motion prediction and uncertainty estimation, further enhanced by Recurrent Neural Networks (RNN) for more accurate predictions. In addition, we develop a receding horizon planning method, formulated as a stochastic optimization problem, to ensure safe, collision-free paths with confidence probabilities. Together, these contributions provide a robust framework for adaptive and safe trajectory generation in dynamic environments. Simulations were performed to demonstrate the effectiveness of the proposed strategy, where our approach (combining GP and RNN) outperformed a baseline method that utilized only GP. 

   more » « less