Rinu Boney
Papers
2
Total Citations
9
H-Index
2
About
Rinu Boney is a robotics researcher focused on bridging the gap between simulation and real-world deployment of reinforcement learning (RL) for autonomous systems. Their key research areas include collision avoidance for mobile robots, low-cost robotic platforms for RL research, and sample-efficient policy learning. Boney’s most notable contribution is the development of SACPlanner, a local planner that leverages Soft Actor-Critic (SAC) with enhancements like RAD and DrQ to achieve near-perfect training in just 10,000 episodes, demonstrating robust real-world collision avoidance on physical robots. This work, with 6 citations, highlights their ability to translate theoretical RL advances into practical navigation solutions. Boney also created RealAnt, an open-source quadruped robot costing only $410, designed to withstand the exploratory controls of RL without the high cost or fragility of existing platforms. This innovation, cited 3 times, makes real-world RL experimentation accessible to a broader research community. By prioritizing affordability and robustness, Boney’s work empowers researchers to validate RL algorithms on physical hardware, accelerating the path from lab to real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2