Zobrazeno 1 - 10
of 128
pro vyhledávání: '"Vadakkepat Prahlad"'
Control system optimization has long been a fundamental challenge in robotics. While recent advancements have led to the development of control algorithms that leverage learning-based approaches, such as SafeOpt, to optimize single feedback controlle
Externí odkaz:
http://arxiv.org/abs/2411.07573
Controller tuning and optimization have been among the most fundamental problems in robotics and mechatronic systems. The traditional methodology is usually model-based, but its performance heavily relies on an accurate mathematical system model. In
Externí odkaz:
http://arxiv.org/abs/2408.16307
A vector-based any-angle path planner, R2, is evolved in to R2+ in this paper. By delaying line-of-sight, R2 and R2+ search times are largely unaffected by the distance between the start and goal points, but are exponential in the worst case with res
Externí odkaz:
http://arxiv.org/abs/2405.04952
R2 is a novel online any-angle path planner that uses heuristic bug-based or ray casting approaches to find optimal paths in 2D maps with non-convex, polygonal obstacles. R2 is competitive to traditional free-space planners, finding paths quickly if
Externí odkaz:
http://arxiv.org/abs/2206.14071
Autor:
Li, Yiting, Zhu, Haiyue, Feng, Xijia, Cheng, Zilong, Ma, Jun, Xiang, Cheng, Vadakkepat, Prahlad, Lee, Tong Heng
This work focuses on tackling the challenging but realistic visual task of Incremental Few-Shot Learning (IFSL), which requires a model to continually learn novel classes from only a few examples while not forgetting the base classes on which it was
Externí odkaz:
http://arxiv.org/abs/2203.10297
Autor:
Liang, Yuanchang, Vadakkepat, Prahlad, Chua, David Kim Huat, Wang, Shuyi, Li, Zhigang, Zhang, Shuxiang
Publikováno v:
In Automation in Construction September 2024 165
Autor:
Li, Yiting, Zhu, Haiyue, Ma, Jun, Teo, Chek Sing, Xiang, Cheng, Vadakkepat, Prahlad, Lee, Tong Heng
Real-world object detection is highly desired to be equipped with the learning expandability that can enlarge its detection classes incrementally. Moreover, such learning from only few annotated training samples further adds the flexibility for the o
Externí odkaz:
http://arxiv.org/abs/2109.11336
Publikováno v:
In Robotics and Autonomous Systems February 2024 172
Autor:
Li, Yiting, Zhu, Haiyue, Tian, Sichao, Feng, Fan, Ma, Jun, Teo, Chek Sing, Xiang, Cheng, Vadakkepat, Prahlad, Lee, Tong Heng
Incremental few-shot learning is highly expected for practical robotics applications. On one hand, robot is desired to learn new tasks quickly and flexibly using only few annotated training samples; on the other hand, such new additional tasks should
Externí odkaz:
http://arxiv.org/abs/2005.02641
Publikováno v:
In Neurocomputing 28 November 2023 559