Imitation Learning (IL) algorithms such as behavior cloning are a promising direction for learning human-level driving behavior. However, these approaches do not explicitly infer the underlying causal structure of the learned task. This often leads to misattribution about the relative importance of scene elements towards the occurrence of a corresponding action, a phenomenon termed causal confusion or causal misattribution. Causal confusion is made worse in highly complex scenarios such as urban driving, where the agent has access to a large amount of information per time step (visual data, sensor data, odometry, etc.). Our key idea is that while driving, human drivers naturally exhibit an easily obtained, continuous signal that is highly correlated with causal elements of the state space: eye gaze. We collect human driver demonstrations in a CARLA-based VR driving simulator, DReyeVR, allowing us to capture eye gaze in the same simulation environment commonly used in prior work. Further, we propose a contrastive learning method to use gaze-based supervision to mitigate causal confusion in driving IL agents — exploiting the relative importance of gazed-at and not-gazed-at scene elements for driving decision-making. We present quantitative results demonstrating the promise of gaze-based supervision improving the driving performance of IL agents.

Robots moving safely and in a socially compliant manner in dynamic human environments is an essential benchmark for long-term robot autonomy. However, it is not feasible to learn and benchmark social navigation behaviors entirely in the real world, as learning is data-intensive, and it is challenging to make safety guarantees during training. Therefore, simulation-based benchmarks that provide abstractions for social navigation are required. A framework for these benchmarks would need to support a wide variety of learning approaches, be extensible to the broad range of social navigation scenarios, and abstract away the perception problem to focus on social navigation explicitly. While there have been many proposed solutions, including high fidelity 3D simulators and grid world approximations, no existing solution satisfies all of the aforementioned properties for learning and evaluating social navigation behaviors. In this work, we propose SocialGym, a lightweight 2D simulation environment for robot social navigation designed with extensibility in mind, and a benchmark scenario built on SocialGym. Further, we present benchmark results that compare and contrast human-engineered and model-based learning approaches to a suite of off-the-shelf Learning from Demonstration (LfD) and Reinforcement Learning (RL) approaches applied to social robot navigation. These results demonstrate the data efficiency, task performance, social compliance, and environment transfer capabilities for each of the policies evaluated to provide a solid grounding for future social navigation research.

Accurate kinodynamic models play a crucial role in many robotics applications such as off-road navigation and high-speed driving. Many state-of-the-art approaches for learning stochastic kinodynamic models, however, require precise measurements of robot states as labeled input/output examples, which can be hard to obtain in outdoor settings due to limited sensor capabilities and the absence of ground truth. In this work, we propose a new technique for learning neural stochastic kinodynamic models from noisy and indirect observations by performing simultaneous state estimation and dynamics learning. The proposed technique iteratively improves the kinodynamic model in an expectation-maximization loop, where the E Step samples posterior state trajectories using particle filtering, and the M Step updates the dynamics to be more consistent with the sampled trajectories via stochastic gradient ascent. We evaluate our approach on both simulation and real-world benchmarks and compare it with several baseline techniques. Our approach not only achieves significantly higher accuracy but is also more robust to observation noise, thereby showing promise for boosting the performance of many other robotics applications.

Robot social navigation is influenced by human preferences and environment-specific scenarios such as elevators and doors, thus necessitating end-user adaptability. State-of-the-art approaches to social navigation fall into two categories: model-based social constraints and learning-based approaches. While effective, these approaches have fundamental limitations – model-based approaches require constraint and parameter tuning to adapt to preferences and new scenarios, while learning-based approaches require reward functions, significant training data, and are hard to adapt to new social scenarios or new domains with limited demonstrations.In this work, we propose Iterative Dimension Informed Program Synthesis (IDIPS) to address these limitations by learning and adapting social navigation in the form of human-readable symbolic programs. IDIPS works by combining pro-gram synthesis, parameter optimization, predicate repair, and iterative human demonstration to learn and adapt model-free action selection policies from orders of magnitude less data than learning-based approaches. We introduce a novel predicate repair technique that can accommodate previously unseen social scenarios or preferences by growing existing policies.We present experimental results showing that IDIPS: 1) synthesizes effective policies that model user preference, 2) can adapt existing policies to changing preferences, 3) can extend policies to handle novel social scenarios such as locked doors, and 4) generates policies that can be transferred from simulation to real-world robots with minimal effort.

Complex robot behaviors are often structured as state machines, where states encapsulate actions and a transition function switches between states. Since transitions depend on physical parameters, when the environment changes, a roboticist has to painstakingly readjust the parameters to work in the new environment. We present interactive SMT- based Robot Transition Repair (SRTR): instead of manually adjusting parameters, we ask the roboticist to identify a few instances where the robot is in a wrong state and what the right state should be. An automated analysis of the transition function 1) identifies adjustable parameters, 2) converts the transition function into a system of logical constraints, and 3) formulates the constraints and user-supplied corrections as a MaxSMT problem that yields new parameter values. We show that SRTR finds new parameters 1) quickly, 2) with few corrections, and 3) that the parameters generalize to new scenarios. We also show that a SRTR-corrected state machine can outperform a more complex, expert-tuned state machine.

Autonomous mobile robots that use multiple depth sensors to perceive their environments, rely on extrinsic calibration to combine the individual views from each sensor into a single coherent view of the surroundings. Such extrinsic calibration is tedious to perform manually, and requires that specific scenes to calibrate. Current state of the art automatic approaches do not consider the content of scenes used for calibration, and thus are not robust to partially informative scenes in long-term deployments. In this paper, we present Delta-Calibration, an automated extrinsic calibration technique that takes into account the information in a scene for calibration. Delta-Calibration relies on constrained sensor motion to minimize the effects of desynchronization, and ego-motion estimation from each depth camera to detect significant changes in pose, which we term Delta-Transforms. We derive a solution to the extrinsic calibration using such Delta-Transforms taking into account uncertain axes of motion in the environment, and further infer necessary and sufficient conditions on the Delta-Transforms such that Delta-Calibration results in a unique, non-singular, and numerically stable extrinsic calibration. We present quantitative and qualitative results demonstrating the effectiveness of Delta-Calibration at computing extrinsic calibration over different arrangements of depth sensors.