Despite the rich theoretical foundation of model-based deep reinforcement learning (RL) agents, their effectiveness in real-world robotics-applications is less studied and understood. In this paper, we, therefore, investigate how such agents generalize to real-world autonomous-vehicle control-tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with high-dimensional LiDAR sensors, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination, substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the observation-model choice. Finally, we provide extensive empirical evidence for the effectiveness of model-based agents provided with long enough memory horizons in sim2real tasks.
The widespread development of driverless vehicles has led to the formation of autonomous racing competitions, where the high speeds and fierce rivalry in motorsport provide a testbed to accelerate technology development. A particular challenge for an autonomous vehicle is that of identifying a target trajectory - or in the case of a racing car, the ideal racing line. Many existing approaches to identifying the racing line are either not the time-optimal solutions, or have solution times which are computationally expensive, thus rendering them unsuitable for real-time application using on-board processing hardware. This paper describes a machine learning approach to generating an accurate prediction of the racing line in real-time on desktop processing hardware. The proposed algorithm is a dense feed-forward neural network, trained using a dataset comprising racing lines for a large number of circuits calculated via a traditional optimal control lap time simulation. The network is capable of predicting the racing line with a mean absolute error of +/-0.27m, meaning that the accuracy outperforms a human driver, and is comparable to other parts of the autonomous vehicle control system. The system generates predictions within 33ms, making it over 9,000 times faster than traditional methods of finding the optimal racing line. Results suggest that a data-driven approach may therefore be favourable for real-time generation of near-optimal racing lines than traditional computational methods.
Autonomous vehicles (AVs) need to share the road with multiple, heterogeneous road users in a variety of driving scenarios. It is overwhelming and unnecessary to carefully interact with all observed agents, and AVs need to determine whether and when to interact with each surrounding agent. In order to facilitate the design and testing of prediction and planning modules of AVs, in-depth understanding of interactive behavior is expected with proper representation, and events in behavior data need to be extracted and categorized automatically. Answers to what are the essential patterns of interactions are also crucial for these motivations in addition to answering whether and when. Thus, learning to extract interactive driving events and patterns from human data for tackling the whether-when-what tasks is of critical importance for AVs. There is, however, no clear definition and taxonomy of interactive behavior, and most of the existing works are based on either manual labelling or hand-crafted rules and features. In this paper, we propose the Interactive Driving event and pattern Extraction Network (IDE-Net), which is a deep learning framework to automatically extract interaction events and patterns directly from vehicle trajectories. In IDE-Net, we leverage the power of multi-task learning and proposed three auxiliary tasks to assist the pattern extraction in an unsupervised fashion. We also design a unique spatial-temporal block to encode the trajectory data. Experimental results on the INTERACTION dataset verified the effectiveness of such designs in terms of better generalizability and effective pattern extraction. We find three interpretable patterns of interactions, bringing insights for driver behavior representation, modeling and comprehension. Both objective and subjective evaluation metrics are adopted in our analysis of the learned patterns.
Roborace team SIT Acronis Autonomous suffered a "computer says no" moment on Thursday when its race car drove straight into a wall, mere seconds after it had started driving. If you're familiar with the Little Britain T.V. show, you'll understand the meaning of "computer says no." And it couldn't be more true for this moment. Luckily no one was hurt. But, you live and you learn, and this is one of the ways people working in robotics learn how to improve their systems.
Robots still have some trouble handling the basics when put to the test, apparently. Roborace team SIT Acronis Autonomous suffered an embarrassment in round one of the Season Beta 1.1 race after its self-driving car abruptly drove directly into a wall. It's not certain what led to the mishap, but track conditions clearly weren't at fault -- the car had been rounding a gentle curve and wasn't racing against others at the same time. It wasn't the only car to suffer a problem, either. Autonomous Racing Graz's vehicle had positioning issues that got it "lost" on the track and cut its race short.
Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments. In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive strategies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. This work makes algorithmic contributions to both challenges. First, to generate a realistic, diverse set of opponents, we develop a novel method for self-play based on replica-exchange Markov chain Monte Carlo. Second, we propose a distributionally robust bandit optimization procedure that adaptively adjusts risk aversion relative to uncertainty in beliefs about opponents' behaviors. We rigorously quantify the tradeoffs in performance and robustness when approximating these computations in real-time motion-planning, and we demonstrate our methods experimentally on autonomous vehicles that achieve scaled speeds comparable to Formula One racecars.
A robotics startup that designs bionic limbs for children in the style of superheroes has raised £4.6 million from investors including the Formula 1 team Williams. Bristol-based Open Bionics became the best-selling multi-grip bionic hand in the UK after launching its Hero Arm in 2018, and plans to use the funding to grow to international markets. Using 3D scanning and 3D printing technologies, the firm has managed to drastically reduce the cost of building robotic prosthetics, allowing the bionic limbs to be covered by national healthcare systems in the UK and abroad. "The Hero Arm is a custom made myoelectric prosthetic. This means users, amputees and people with limb differences below the elbow, can control their new bionic fingers by squeezing the muscles in their forearms," Open Bionics co-founder Samantha Payne told The Independent.
Once a year, the bucolic grounds of Goodwood House in West Sussex, England, are consumed by the smell of exhaust fumes, the sound of engines revving, and an excited crowd of 100,000 people, all wanting a look at the special cars on show. They gather here because Charles Gordon-Lennox, the 11th Duke of Richmond, likes to occasionally open his home to host the Goodwood Festival of Speed, a celebration of all the history, the heritage, and the future of motor racing. This week, among the supercars, hypercars, and pure racing cars, Goodwood visitors will spot a low, black machine streaking in near silence up the winding driveway to the estate, which for the event is transformed into a 1.16-mile hill climb track. "We're pretty sure when the car appears, people will freak out," says Rod Chong, deputy CEO of Roborace. And it will be the first machine to give the hill climb a try without a human in command, so there are some nerves.
A self driving robotic racing car is set to take on the world's best human drivers at the Goodwood Festival of Speed. The Roborace car, which is powered by four 135kW electric motors and uses an artificial intelligence driver, will drive up the event's 1.16-mile hillclimb course, famed for its tight turns, hay bales, flint walls and forests. It has previously raced city circuits around the world as part of the Formula E race series. The Roborace car, which is powered by four 135kW electric motors and uses an artificial intelligence driver, will drive up the event's 1.16-mile hillclimb course, the first time an autonomous vehicle has been allowed to compete'We are excited that the Duke of Richmond [FoS founder] has invited us to make history at Goodwood as we attempt the first ever fully - and truly - autonomous uphill climb using only artificial intelligence,' said Lucas di Grassi, Roborace CEO. The automated driving system the Roborace car will use at Goodwood has been developed by automotive technology company Arrival.