We use the Virtual Autonomous Vehicle Simulation (VAVS) TDP for initial development, analysis and testing of autonomous vehicles. This study is often moved to the next level by using the Scaled Autonomous Vehicle Indoor (SAVI) TDP. As we move further to full scale real hardware for autonomous vehicles, we believe that there is an intermediate stage of evaluating our strategies on a lower speed platform with relatively lesser risk, leading to the current TDP.
Further, lower speed autonomous vehicles also offer a unique value proposition on their own, as low speed vehicles are typically used in scenarios that involve high densities of people (such as in college campuses) and/or in scenarios where there is constant interaction with a multitude of people (such as in shuttle services). This then becomes a rich environment to study aspects of human-vehicle interactions as it relates to safety and human trust in autonomous vehicles.
The Low Speed Autonomous Vehicle (LSAV) Technology Demonstrator Platform will be based on one or more electric-golf-cart-type vehicles, that will be modified to have autonomous functionality. The vehicles will be modified to be drive-by-wire, sensors and compute platform added, so that we can download and evaluate our autonomous vehicle strategies.
The low-speed nature of the vehicles will allow us to more readily engage in experiments in crowded scenarios such as our Texas A&M College Campus. We intend to deploy the LSAV-TDPs as shuttle and/or on-demand-transit services both on and off the campus, and use such initiatives to provide us with rich information on the human-vehicle interactions. In turn we will be performing research on how to design the human-vehicle interactions to improve both safety and trustworthiness of autonomous vehicles.
- A Polaris GEM (electric golf cart) has been converted to autonomous vehicle. The autonomous vehicle is equipped with LIDARs, Cameras, Radars, GPS, IMU, etc. as well as powerful on-board computers.
- Additional golf-carts are being planned to provide “fleets” of autonomous vehicles for shuttle services.
- Multiple projects are on-going leveraging this TDP
Projects Leveraging the TDP
- Autonomous Shuttle Our goal is to develop and deploy Autonomous Shuttles on Texas A&M Campus and other private campuses such as hotels, golf courses etc. To this end we are interested in developing robust localization, mapping, obstacle avoidance and control algorithms.
- Formalizing Human-Machine Communication in the context of Autonomous Vehicles While driving behavior is generally governed by the nature and driving objectives of the driver, there are many situations (typically in crowded traffic conditions) where tacit communication between the drivers and pedestrians govern the overall driving behavior, significantly enhancing driving safety. We intend to study and formalize the communication pattern between human drivers and pedestrians, as also investigate effective communication mechanisms between an autonomous vehicle and humans. Current autonomous vehicles engage in decision making that is primarily driven by on-board or external sensory information, and do not explicitly consider communication with pedestrians. We will incorporate the formalized communications from this study into decision making algorithms of an autonomous vehicle. Use of the results of this study would lead to improved safety of both autonomous vehicles as well as conventional vehicles.