SJTU Pujiang International College PhD Student Publishes First-Author Paper on Robot Target Search in IEEE T-RO
浦江国际学院博士生在机器人顶刊IEEE T-RO发表一作论文
Yunpeng Lu, a 2024 doctoral student at Shanghai Jiao Tong University's Pujiang International College, has been accepted as first author of a paper titled 'RPT*: Global Planning with Probabilistic Terminals for Target Search in Complex Environments' in IEEE Transactions on Robotics. The work, co-authored with Carnegie Mellon University and developed at the RAP Lab, introduces RPT*, an algorithm with optimality guarantees for target search under uncertainty, and the hierarchical autonomous target search system HATS. Validated in simulation and on real robots (quadruped and wheeled), the system addresses probabilistic termination in Hamiltonian path problems, achieving significant speedups over integer programming and outperforming greedy and reinforcement learning baselines in expected path cost.
Source: Chinese robotics — Research news discovery · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S5
Reported numbers
Reported success rate
100%
Reported trials
elapsed time
152 seconds
elapsed time
104 seconds
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
研究面向复杂环境下移动机器人目标搜索问题,提出了一类具备最优性保证的全局规划算法RPT*,构建出层次化自主目标搜索系统HATS,目前已在仿真环境与真实机器人平台上完成完整验证。
Open source S5
在未知环境搜索(HATS-U)实验中,RPT*在准确先验和误导性先验两种场景下均实现了100%成功率。
Open source S17
左:四足机器人在40×30米走廊环境中搜索目标(书包),任务时长152秒。
Open source S20
右:轮式机器人在30×20米实验室环境中搜索目标(垃圾桶),任务时长104秒。
Open source S21
Source:Chinese robotics — Research news discovery · news.sjtu.edu.cn