Across the globe, hundreds of thousands of workers rise from their beds in the middle of the night to climb into the tight quarters of the cabin of a big rig. This workforce hauls billions of tons of cargo every year to warehouses, groceries stores, and ports. The shipping industry moves nearly 11 billion tonnes (12 billion tons) of freight via human-driven big rigs annually.
With autonomous trucks, TuSimple can make highways safer for truckers and other drivers alike, all while saving money on the transport of crucial goods.
While these rigs are essential to the movement of supply chains around the world, the industry faces a rising driver shortage. The trucking industry has struggled to both retain its existing workforce and certify new drivers, especially as driving schools closed during the COVID-19 pandemic. These circumstances combined have made it difficult for trucking to meet rising demands for supplies ranging from fuel to electronics.
TuSimple fleet of autonomous trucks. (Image credit: TuSimple)
长途大型钻机也是一名工人安全噩梦。长时间，经常开车穿过夜晚或清晨，卡车司机比其他司机更容易疲劳。CDC表示疲劳驾驶危及在陶醉时尽可能多地驾驶。
It was in this combination of problems facing the trucking industry that Xiaoling Han and colleagues atTuSimplesaw the opportunity for a new kind of solution: autonomous technology for heavy-duty trucks.
汉族，TusiMple的传感器高级总监和车辆控制整合说，这些车辆可以解决货运行业的巨大问题。“自动卡车提供了比自动汽车更强大的商业案例，因为航线是高度可重复的，并且大多数驾驶在高速公路上发生，”汉班说。“在解决卡车的自主驾驶问题的同时非常困难，它的问题越来越少，而不是自主车。”
With autonomous trucks, Han says TuSimple can make highways safer and more efficient while helping reduce costs and the environmental footprint of trucks.
The Road to Autonomy
It’s not uncommon to see technology across a wide range of industries labeled as autonomous these days, from robot vacuums to your new car. But when it comes to true autonomy, many of these technologies fall short, explains Govind Malleichervu, automotive industry manager at MathWorks.
Level 4 or 5 autonomous trucks would give drivers an opportunity to rest while driving through the night on empty roads.
As defined by the Society of Automotive Engineers, there are six possible levels of autonomy for automotive vehicles, ranging from zero to five. Levels 0 through 3 range from no automation to limited automation, including assisted steering or braking. Due to the limited capabilities, human drivers still control the vehicle and supervise these systems. Level 5 autonomy, where the vehicle performs all driving tasks, is still many years away.
“Automated driving features offered by many OEMs are at Level 2 or Level 2+,” Malleichervu says, where the plus designates increased autonomy without quite reaching Level 3. “With these levels, the advanced driver assistance system (ADAS) on the vehicle controls the braking system, accelerating, and steering, with the human driver still responsible for monitoring the environment at all times and performing all other driving tasks.”
这种相对有限的自主水平是部分原因是安全问题，在城市环境中的车辆中的测试和开发ADAS固有。
This is where TuSimple’s trucks have an advantage, Han says. While the company doesn’t expect its trucks to be out on the road in full force until at least 2024, testing this technology on less densely driven highways instead of city centers offers an easier path toward achieving full autonomy. To test autonomous vehicles in a city, companies must first come to agreements with local authorities on where, how often, and at what speeds their vehicles can be tested. This often means reducing the area and time available for testing.
Another bonus for highway testing is that it faces fewer pedestrian obstacles than in cities and largely avoids stop-and-go traffic and narrow or uneven roads. While this doesn’t completely remove the risk of harm to other drivers should something go wrong, it does lessen the likelihood of a deadly accident.
Right now, Han says that TuSimple’s trucks are at Level 4 autonomy. This means that the vehicles can drive themselves under limited conditions without the assistance of a human driver—although in TuSimple’s case the company plans to still have human drivers supervise from the driver’s seat. Unlike trucking today, which requires constant vigilance from human drivers, Level 4 or 5 autonomous trucks would give them an opportunity to rest while driving through the night on empty roads.
这种自治的一个关键方面，汉族和他的团队一直在开发的是一种自主的绕线制动系统。大型钻机的重量以及与拉动完全装载的拖车相关联的动力量使它们更加困难，以便快速停止。完全装载的卡车可以重达36,000公斤（80,000磅），而乘用车的重量更接近1,360千克（3,000磅）。制动系统必须能够安全地停止在公路速度下行驶的重型卡车的势头。
“The by-wire braking system is very complex,” says Han. “The whole pipeline starts from perception, where our program looks at its surroundings in the front and back of the vehicle. This includes motion planning, prediction, and the control algorithm.”
Using perception and sensors such as lidar, TuSimple’s L4 autonomous system sees 360 degrees around the vehicle and 1,000 meters in front of it. The data is then passed along to the safety-critical brake-by-wire control system, Han explains, which then makes the connection between software perceptions to the truck’s hardware to activate safe braking.
“刹车是最fundamental system in autonomous driving,” says Han. “The safety level for braking is above all the other systems.”
These stricter standards for the braking system are also reflected in its redundancies, Han explains, which allow human controllers to intervene and brake manually if something goes wrong.
“对于车辆的其他部分，例如发动机，一定程度的冗余将足够，”韩说。“然而，因为制动系统是车辆中最安全的关键部分，我们必须具有完全冗余，包括物理，信号，电源和软件系统。”
Trust in the Model
TuSimple is already testing its big rigs on real highways, including a 951-mile trek from Arizona to Oklahoma to deliver watermelons. However, the costs of relying entirely on-road testing can add up quickly, Han explains. Instead, the team largely relies on modeling and simulations as a safe and cost-effective alternative for the by-wire control development. According to Han, as much as 90% of the trucks’ vehicle control unit testing is done using models developed in MATLAB®, Simulink®和其他软件。
通过使用模型，团队引用一个单一的真理来源，自动生成代码，并可以测试具有不同车辆限制的自主系统。
“对于绕线制动，我们只在车辆等级中测试了10％的时间，因为它的成本越来越高，”汉族说。“它消耗了人力力量并需要额外的协调。因此，我们在模拟中做了大部分测试。“
模拟需要建模不同的传感器输入，例如激光雷达和雷达，通过微处理器转发到卡车的物理控制系统。通过模型管理这些组件使团队成员能够同时在设计上工作，即使它们从不同的物理位置工作。
A TuSimple driver lets autonomous driving take over. (Video credit: TuSimple)
“The team can refer to the model to check what’s going on inside the vehicle,” Han says. “It’s much easier than reading the code. That’s why the model is the single source of truth for the whole Vehicle Control Unit team, because we can communicate based on the model across all related functional teams.”
Malleichervu说，该模型还通过自动生成代码来减少人类编码器引入的错误，以便在Malleichervu表示在模型级别的设计中实现设计。这种方法使该团队能够测试具有不同车辆限制的自治系统，例如不同的发动机或货物重量。该团队依赖于Matlab脚本和Github来管理变体。
打破模具
Beyond simplicity, Han says that relying primarily on virtual models to test their new designs also helps them break free of a standard design model across the automotive and software industry called theV-model.
“我们有一个非常快速的迭代期，这意味着我们在一个月内释放软件而不是一年。...在没有建模的情况下，很难在一个月内释放一个功能，因为在那个月内需要完成编码，测试，验证，一切。“
Xiaoling Han, senior director of sensors and vehicle control integration at TuSimple
TuSimple combines V-model and Agile methodology to create their ideal design process. (Image credit: TuSimple)
又称验证和验证模型，V模型是一种设计方法，可以通过在实现新功能之前通过分析，设计和验证系统地移动。因此，Malleichervu表示，从开始使用V模型开始发动机或车辆程序通常需要三到五年;对现有设计实施升级需要大约一年。
For TuSimple, this methodology was too slow, Han says. Instead, the company implemented a mixed method that includes both the V-model and Agile methods when developing their autonomous systems.
“我们有一个非常快的迭代周期,这意味着we release by-wire control software in weeks rather than years,” says Han. “That’s why we need to follow the Agile process as well. That’s also why we rely on modeling. Without modeling, it’s very hard to release a feature in a month, because in that month you need to finish the coding, testing, validation, everything.”
Using this hybrid approach, TuSimple can release by-wire software patches in less than 24 hours and new features anywhere between 72 hours and two weeks. It’s this novel design method and TuSimple’s use of modeling that Han thinks will help the company reach its goal of hitting the highways with autonomous big rigs by 2024.
