A proof-of-concept multi-robot platform for risk-aware navigation, autonomous package delivery, preference-aware mobility, integrated perception, smart patrolling, and an API for future campus applications.
In this project, reasoning under both aleatoric and epistemic uncertainty, we seek to design a proof-of-concept Multi-robot Symbiotic Autonomy Platform (MSAP) and synthesize provably efficient controllers and algorithms for safety-critical applications in transportation and last-mile logistics.
Capitalizing on the infrastructure and equipment already in place at KU’s Autonomous Vehicle Lab — including an autonomous shuttle service at the SAN campus, contactless robotic delivery vehicle, retrofitted autonomous Nissan Leaf car, legged robot, robotic arm, and four drones — we develop an MSAP operating system that enables:
- Risk-aware multi-agent navigation through collective autonomous intelligence and collective risk assessment
- Autonomous small-package delivery under epistemic and aleatoric uncertainty
- User-centered passenger mobility service via preference elicitation integrated into the vehicle navigation stack
- Integrated multi-agent perception that captures objects beyond line-of-sight of a single agent
- Smart monitoring and patrolling for outdoor facilities such as parking areas, outdoor storage areas, and construction sites
- An application programming interface (API) hosted on AV Lab servers for future app development on the integrated platform
Figures
