Christian Ellis
Papers
1
Total Citations
2
H-Index
1
About
Christian Ellis is a researcher advancing the intersection of robotics, machine learning, and human-robot interaction, with a primary focus on autonomous navigation and reward learning from human demonstration. Their most-cited work, "Risk Averse Bayesian Reward Learning for Autonomous Navigation from Human Demonstration" (2021), introduces a novel framework that combines Bayesian inference with risk-sensitive decision-making, enabling robots to infer reward functions from non-expert demonstrations while accounting for uncertainty and safety. This contribution is particularly significant for real-world deployment, where robots must navigate complex, dynamic environments without requiring machine learning expertise from human teachers. While still early in their career, Ellis’s research addresses a critical gap in imitation learning: balancing fidelity to human preferences with robust, risk-aware behavior. Their work has implications for assistive robotics, autonomous vehicles, and collaborative systems, where safe and intuitive human teaching is paramount. With 2 citations on their flagship paper, Ellis is building a foundation for more trustworthy and accessible robot learning, positioning them as an emerging voice in safe autonomy and human-centered AI.
Research Focus
Key Achievements
Top Papers
- 1