Masafumi Endo
Papers
2
Total Citations
5
H-Index
2
About
Masafumi Endo is a roboticist focused on advancing autonomous navigation in complex, off-road environments. His primary research areas include model-based control, motion planning, and traversability analysis for mobile robots. Endo’s major contribution is addressing the critical problem of local minima entrapment in robotic navigation—a common failure mode where planners get stuck in suboptimal paths. In his most cited work, "Towards Local Minima-free Robotic Navigation," he introduces a Model Predictive Path Integral (MPPI) controller augmented with repulsive potential fields, enabling robots to escape local minima without sacrificing solution quality. This work has garnered 3 citations since 2025, signaling growing interest in his approach. Additionally, Endo developed "BenchNav," a simulation platform for benchmarking off-road navigation algorithms with probabilistic traversability, which has received 2 citations. This tool addresses the challenge of selecting appropriate planning methods amid algorithmic diversity, providing a standardized evaluation framework. Endo’s work is notable for bridging the gap between theoretical control methods and practical deployment in unstructured terrains, making him a rising figure in field robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2