Josh H. McDermott
Papers
3
Total Citations
52
H-Index
3
About
Josh H. McDermott is a leading researcher at the intersection of artificial intelligence, robotics, and embodied perception, with a core focus on visually-guided task-and-motion planning and audio-visual integration. His most impactful work centers on the ThreeDWorld Transport Challenge, a benchmark that pushes the boundaries of physically realistic embodied AI by requiring agents to navigate simulated home environments, manipulate objects with articulated arms, and complete complex transport tasks. This benchmark, introduced in 2021 and refined in 2022, has garnered 39 combined citations, establishing it as a key resource for the community. McDermott’s research also explores how asynchronous sensory cues—such as hearing an object fall and then visually locating it—can be integrated to improve robotic perception and action. His 2022 paper on "Finding Fallen Objects Via Asynchronous Audio-Visual Integration" (13 citations) demonstrates the practical value of combining vision and audition for real-world tasks. Through these contributions, McDermott is advancing the development of AI systems that can perceive, reason, and act in complex, dynamic environments, bridging the gap between simulation and reality.
Research Focus
Key Achievements
Top Papers
- 1
- 2Finding Fallen Objects Via Asynchronous Audio-Visual Integration13 citations · 2022
- 3