Many applications of imitation learning require the agent to generate the full distribution of behaviour observed in the training data. For example, to evaluate the safety of autonomous vehicles in simulation, accurate and diverse behaviour models of other road users are paramount. Existing methods that improve this distributional realism typically rely on hierarchical policies. These condition the policy on types such as goals or personas that give rise to multi-modal behaviour. However, such methods are often inappropriate for stochastic environments where the agent must also react to external factors: because agent types are inferred from the observed future trajectory during training, these environments require that the contributions of internal and external factors to the agent behaviour are disentangled and only internal factors, i.e., those under the agent's control, are encoded in the type. Encoding future information about external factors leads to inappropriate agent reactions during testing, when the future is unknown and types must be drawn independently from the actual future. We formalize this challenge as distribution shift in the conditional distribution of agent types under environmental stochasticity. We propose Robust Type Conditioning (RTC), which eliminates this shift with adversarial training under randomly sampled types. Experiments on two domains, including the large-scale Waymo Open Motion Dataset, show improved distributional realism while maintaining or improving task performance compared to state-of-the-art baselines.

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for safety and reliability concerns. In this paper, we show how imitation learning combined with reinforcement learning using simple rewards can substan-tially improve the safety and reliability of driving policies over those learned from imitation alone. In particular, we train a policy on over lOOk miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision likelihood. Our analysis shows that while imitation can perform well in low-difficulty scenarios that are well-covered by the demonstration data, our proposed approach significantly improves robustness on the most challenging scenarios (over 38 % reduction in failures). To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real- world human driving data.

Simulation is an essential tool to develop and benchmark autonomous vehicle planning software in a safe and cost-effective manner. However, realistic simulation requires accurate modeling of multi-agent interactive behaviors to be trustworthy, behaviors which can be highly nuanced and complex. To address these challenges, we introduce Waymax, a new data-driven simulator for autonomous driving in multi-agent scenes, designed for large-scale simulation and testing. Waymax uses publicly-released, real-world driving data (e.g., the Waymo Open Motion Dataset) to initialize or play back a diverse set of multi-agent simulated scenarios. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training, making it suitable for modern large-scale, distributed machine learning workflows. To support online training and evaluation, Waymax includes several learned and hard-coded behavior models that allow for realistic interaction within simulation. To supplement Waymax, we benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions, where we highlight the effectiveness of routes as guidance for planning agents and the ability of RL to overfit against simulated agents.

Simulation with realistic, interactive agents represents a key task for autonomous vehicle software development. In this work, we introduce the Waymo Open Sim Agents Challenge (WOSAC). WOSAC is the first public challenge to tackle this task and propose corresponding metrics. The goal of the challenge is to stimulate the design of realistic simulators that can be used to evaluate and train a behavior model for autonomous driving. We outline our evaluation methodology, present results for a number of different baseline simulation agent methods, and analyze several submissions to the 2023 competition which ran from March 16, 2023 to May 23, 2023. The WOSAC evaluation server remains open for submissions and we discuss open problems for the task.

Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such cars. Such models can be obtained by applying learning from demonstration (LfD) to trajectories observed by cars already on the road. However, existing LfD methods are typically insufficient, yielding policies that frequently collide or drive off the road. To address this problem, we propose Symphony, which greatly improves realism by combining conventional policies with a parallel beam search. The beam search refines these policies on the fly by pruning branches that are unfavourably evaluated by a discriminator. However, it can also harm diversity, i.e., how well the agents cover the entire distribution of realistic behaviour, as pruning can encourage mode collapse. Symphony addresses this issue with a hierarchical approach, factoring agent behaviour into goal generation and goal conditioning. The use of such goals ensures that agent diversity neither disappears during adversarial training nor is pruned away by the beam search. Experiments on both proprietary and open Waymo datasets confirm that Symphony agents learn more realistic and diverse behaviour than several baselines.

We introduce a motion forecasting (behavior prediction) method that meets the latency requirements for autonomous driving in dense urban environments without sacrificing accuracy. A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency. In addition to predicting trajectories, our scene encoder lends itself to predicting whole-scene probabilistic occupancy grids, a complementary output representation suitable for busy urban environments. Occupancy grids allow the AV to reason collectively about the behavior of groups of agents without processing their individual trajectories. We demonstrate the effectiveness of our sparse input representation and our model in terms of computation and accuracy over three datasets. We further show that co-training consistent trajectory and occupancy predictions improves upon state-of-the-art performance under standard metrics.

We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL using a hierarchical model to enable generalization to arbitrary goal routes, and measure performance using a closed-loop evaluation framework with simulated interactive agents. We train policies from expert trajectories collected from real vehicles driving over 100,000 miles in San Francisco, and demonstrate a steerable policy that can navigate robustly even in a zero-shot setting, generalizing to synthetic scenarios with novel goals that never occurred in real-world driving. We also demonstrate the importance of mixing closed-loop MGAIL losses with open-loop behavior cloning losses, and show our best policy approaches the performance of the expert. We evaluate our imitative model in both average and challenging scenarios, and show how it can serve as a useful prior to plan successful trajectories.

We propose a unified framework for image retrieval capable of handling complex and descriptive queries of multiple modalities in a scalable manner. A novel aspect of our approach is that it supports query specification in terms of objects, attributes and spatial relationships, thereby allowing for substantially more complex and descriptive queries. We allow these complex queries to be specified in three different modalities - images, sketches and structured textual descriptions. Furthermore, we propose a unique multi-modal hashing algorithm capable of mapping queries of different modalities to the same binary representation, enabling efficient and scalable image retrieval based on multi-modal queries. Extensive experimental evaluation shows that our approach outperforms the state-of-the-art image retrieval and hashing techniques on the MSRC and SUN09 datasets by about 100%, while the performance on a dataset of 1M images, from Flickr, demonstrates its scalability.

We present a prototype system for interactive construction and modification of 3D physical models using building blocks. Our system uses a depth sensing camera and a novel algorithm for acquiring and tracking the physical models. The algorithm, Lattice-First, is based on the fact that building block structures can be arranged in a 3D point lattice where the smallest block unit is a basis in which to derive all the pieces of the model. The algorithm also makes it possible for users to interact naturally with the physical model as it is acquired, using their bare hands to add and remove pieces. We present the details of our algorithm, along with examples of the models we can acquire using the interactive system. We also show the results of an experiment where participants modify a block structure in the absence of visual feedback. Finally, we discuss two proof-of-concept applications: a collaborative guided assembly system where one user is interactively guided to build a structure based on another user's design, and a game where the player must build a structure that matches an on-screen silhouette.

The multimedia information retrieval community has dedicated extensive research effort to the problem of content-based image retrieval (CBIR). However, these systems find their main limitation in the difficulty of creating pictorial queries. As a result, few systems offer the option of querying by visual examples, and rely on automatic concept detection and tagging techniques to provide support for searching visual content using textual queries.

The lack of access to visual information like text labels, icons, and colors can cause frustration and decrease independence for blind people. Current access technology uses automatic approaches to address some problems in this space, but the technology is error-prone, limited in scope, and quite expensive. In this paper, we introduce VizWiz, a talking application for mobile phones that offers a new alternative to answering visual questions in nearly real-time - asking multiple people on the web. To support answering questions quickly, we introduce a general approach for intelligently recruiting human workers in advance called quikTurkit so that workers are available when new questions arrive. A field deployment with 11 blind participants illustrates that blind people can effectively use VizWiz to cheaply answer questions in their everyday lives, highlighting issues that automatic approaches will need to address to be useful. Finally, we illustrate the potential of using VizWiz as part of the participatory design of advanced tools by using it to build and evaluate VizWiz::LocateIt, an interactive mobile tool that helps blind people solve general visual search problems.

A common trait of background subtraction algorithms is that they have learning rates, thresholds, and initial values that are hand-tuned for a scenario in order to produce the desired subtraction result; however, the need to tune these parameters makes it difficult to use state-of-the-art methods, fuse multiple methods, and choose an algorithm based on the current application as it requires the end-user to become proficient in tuning a new parameter set. The proposed solution is to automate this task by using a Particle Swarm Optimization (PSO) algorithm to maximize a fitness function compared to provided ground-truth images. The fitness function used is the F-measure, which is the harmonic mean of recall and precision. This method reduces the total pixel error of the Mixture of Gaussians background subtraction algorithm by more than 50% on the diverse Wallflower data-set.