**5. Conclusion**

**3.5. Crowdsourcing**

12 Autonomous Vehicle

system.

needs to be ensured.

and cloud-based fault tolerant control.

Crowdsourcing can be defined as a process to obtain desired information, service, input or ideas on a specific task (which surpass computer capabilities) from human(s), typically over the Internet [60, 61]. In case of autonomous vehicles, crowdsourcing can be performed to solve a number of problems, for example, during operation vehicles identify new obstacles/routes which were not labelled previously and require human(s) input. Standalone implementations limit vehicles' ability for accomplishing such objectives [5]. Cloud-enabled systems facilitate in conducting crowdsourcing activities with specific or cloud crowd [61]. Cloud-based crowdsourcing has captured much attention of the researchers and industrialists/enterprises to achieve automation in their different processes [61]. A prominent example of cloud-based crowdsourcing is Amazon's Mechanical Turk (MTurk), which provides marketplace to perform tasks that surpass computer capabilities and require human intelligence [62].

In this section, we have summarized different potential research challenges and future

**• Effective load balancing:** New algorithms and policies are required for balancing compu‐

**• Scalable parallelization:** Advancements in the cloud infrastructure are required for cloud computing parallelization scheme to scale based upon the size of autonomous vehicular

**• Effective sampling and scaling of data:** New algorithms and approaches are required,

**• Ensure privacy and security:** The data collected through different autonomous vehicles (using sensors, cams, route maps, etc.) can include potential secretes (e.g. private home data, corporate business planes, etc.), and over cloud it can be prone to theft or criminal use.

**• Ensure control and safety:** The control of autonomous vehicles over cloud can be exposed to potential hacking threats. A hacker could remotely control the vehicle and use it for unethical purpose or to cause certain damage. Hence, the control and safety of the vehicle

**• Cope with varying network latency and QoS:** For real-time applications, new algorithms

**• Fault tolerant control:** For autonomous vehicular system failures can lead to undesirable hazardous situations, hence are not acceptable. New approaches are required for onboard

**• Verification and validation of the system:** A primary problem for the autonomous vehicular system is the ability to substantiate that the system can operate safely, effectively

which scale to the size of big data and are more robust to dirty data [56].

Hence, privacy and security of the data over cloud needs to be ensured.

and approaches are needed to handle varying network latency and QoS.

**4. Research challenges and future directions**

tations between vehicle's onboard and cloud computers.

directions for cloud-enabled autonomous vehicles.

In this chapter, we have provided an overview of the evolution of the cloud robotics and autonomous vehicles through different phases of the history. We discussed that automation of different types of vehicles (e.g. on-road, off-road, water, aerial, space and amphibious vehicle) can increase the safety, reliability, robustness and efficiency of the system. We examined that autonomous vehicle is an active area of research with rich history, and it possesses great potential in numerous challenging applications. We analysed that the cloud robotics paradigm enabled new approaches, where autonomous vehicles are not limited to onboard capabilities and relies on data from a cloud network to support their different operations. Cloud provides economics of scale and facilitates backup and sharing of data across different agents. We also discussed potential of cloud to enhance automation of vehicles by improving performance though different potential benefits including cloud computing, big data, open-source/open-access, system learning and crowdsourcing. In the end we analysed different active research challenges and possible future directions in the field.

The chapter can help new researchers in the field to get an overview of the current state-ofthe-art systems and start research activities in possible future directions. We believe that a comprehensive design of autonomous vehicular systems based on cloud infrastructure can significantly increase the reliability, robustness and safety of autonomous vehicles that can be exploited for different potential applications.
