As AI systems increasingly engage in social interactions, comprehending human social dynamics is crucial. Affect recognition enables systems to respond appropriately to emotional nuances in social situations. However, existing multimodal approaches lack accounting for the social appropriateness of detected emotions within their contexts. This paper presents a novel methodology leveraging sentence embeddings to distinguish socially appropriate and inappropriate interactions for more context-aware AI systems. Our approach measures the semantic distance between facial expression descriptions and predefined reference points. We evaluate our method using a benchmark dataset and a real-world robot deployment in a library, combining GPT-4(V) for expression descriptions and ada-2 for sentence embeddings to detect socially inappropriate interactions. Our results underscore the importance of considering contextual factors for effective social interaction understanding through context-aware affect recognition, contributing to the development of socially intelligent AI capable of interpreting and responding to human affect appropriately.

Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is open-sourced at https://github.com/KTH-RPL/SeFlow.

Real-world human-robot interactions often encompass uncertainty. This uncertainty can be handled in different ways, for example by designing robot planners to be more or less risk-tolerant. However, how users actually perceive different risk-taking behaviours in robots has yet to be described. Additionally, in the absence of guarantees on optimal robot performance, the interaction between risk and performance on user perceptions is also unclear. To address this gap, we conducted a user study with 84 participants investigating how robot performance and risk behaviour affects users' trust and risk-taking decisions. Participants collaborated with a Franka robot arm to perform a block-stacking task. We compared a robot which displays consistent but sub-optimal behaviours to a robot displaying risky but occasionally optimal behaviour. Risky robot behaviour led to higher trust than consistent behaviour when the robot was on average good at stacking blocks (high expectation), but lower trust when the robot was on average bad at stacking blocks (low expectation). Individual risk-willingness also predicted likelihood of selecting the risky robot over the consistent robot for future interactions, but only when the average expectation was low. These findings have implications for risk-aware planning and decision-making in mixed human-robot systems.

Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor noise. These challenges become more evident in highly dynamic environments. This work proposes a probabilistic framework to jointly infer which parts of an environment are statically and which parts are dynamically occupied. We formulate the problem as a Bayesian network and introduce minimal assumptions that significantly reduce the complexity of the problem. Based on those, we derive Transitional Grid Maps (TGMs), an efficient analytical solution. Using real data, we demonstrate how this approach produces better maps than the state-of-the-art by keeping track of both static and dynamic elements and, as a side effect, can help improve existing SLAM algorithms.

Data annotation in autonomous vehicles is a critical step in the development of Deep Neural Network (DNN) based models or the performance evaluation of the perception system. This often takes the form of adding 3D bounding boxes on time-sequential and registered series of point-sets captured from active sensors like Light Detection and Ranging (LiDAR) and Radio Detection and Ranging (RADAR). When annotating multiple active sensors, there is a need to motion compensate and translate the points to a consistent coordinate frame and timestamp respectively. However, highly dynamic objects pose a unique challenge, as they can appear at different timestamps in each sensor's data. Without knowing the speed of the objects, their position appears to be different in different sensor outputs. Thus, even after motion compensation, highly dynamic objects are not matched from multiple sensors in the same frame, and human annotators struggle to add unique bounding boxes that capture all objects. This article focuses on addressing this challenge, primarily within the context of Scania-collected datasets. The proposed solution takes a track of an annotated object as input and uses the Moving Horizon Estimation (MHE) to robustly estimate its speed. The estimated speed profile is utilized to correct the position of the annotated box and add boxes to object clusters missed by the original annotation.

In this letter, we tackle the challenge of predicting the unseen walls of a partially observed environment as a set of 2D line segments, conditioned on occupancy grids integrated along the trajectory of a 360(degrees) LIDAR sensor. A dataset of such occupancy grids and their corresponding target wall segments is collected by navigating a virtual robot between a set of randomly sampled waypoints in a collection of office-scale floor plans from a university campus. The line segment prediction task is formulated as an autoregressive sequence prediction task, and an attention-based deep network is trained on the dataset. The sequence-based autoregressive formulation is evaluated through predicted information gain, as in frontier-based autonomous exploration, demonstrating significant improvements over both non-predictive estimation and convolution-based image prediction found in the literature. Ablations on key components are evaluated, as well as sensor range and the occupancy grid's metric area. Finally, model generality is validated by predicting walls in a novel floor plan reconstructed on-the-fly in a real-world office environment.

Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for probabilistic methods that support multiple hypotheses for robot's pose. We propose such a probabilistic method to predict the posterior distribution of camera poses given an observed image. Our proposed training strategy results in a generative model of camera poses given an image, which can be used to draw samples from the pose posterior distribution. Our method is streamlined and well-founded in theory and outperforms existing methods on localization in presence of ambiguities.

3D object detection at long-range is crucial for ensuring the safety and efficiency of self-driving vehicles, allowing them to accurately perceive and react to objects, obstacles, and potential hazards from a distance. But most current state-of-the-art LiDAR based methods are range limited due to sparsity at long-range, which generates a form of domain gap between points closer to and farther away from the ego vehicle. Another related problem is the label imbalance for faraway objects, which inhibits the performance of Deep Neural Networks at long-range. To address the above limitations, we investigate two ways to improve long-range performance of current LiDAR-based 3D detectors. First, we combine two 3D detection networks, referred to as range experts, one specializing at near to mid-range objects, and one at long-range 3D detection. To train a detector at long-range under a scarce label regime, we further weigh the loss according to the labelled point's distance from ego vehicle. Second, we augment LiDAR scans with virtual points generated using Multimodal Virtual Points (MVP), a readily available image-based depth completion algorithm. Our experiments on the long-range Argoverse2 (AV2) dataset indicate that MVP is more effective in improving long range performance, while maintaining a straightforward implementation. On the other hand, the range experts offer a computationally efficient and simpler alternative, avoiding dependency on image-based segmentation networks and perfect camera-LiDAR calibration.

In the field of robotics, the point cloud has become an essential map representation. From the perspective of downstream tasks like localization and global path planning, points corresponding to dynamic objects will adversely affect their performance. Existing methods for removing dynamic points in point clouds often lack clarity in comparative evaluations and comprehensive analysis. Therefore, we propose an easy-to-extend unified benchmarking framework for evaluating techniques for removing dynamic points in maps. It includes refactored state-of-art methods and novel metrics to analyze the limitations of these approaches. This enables researchers to dive deep into the underlying reasons behind these limitations. The benchmark makes use of several datasets with different sensor types. All the code and datasets related to our study are publicly available for further development and utilization.

Visual localization allows autonomous robots to relocalize when losing track of their pose by matching their current observation with past ones. However, ambiguous scenes pose a challenge for such systems, as repetitive structures can be viewed from many distinct, equally likely camera poses, which means it is not sufficient to produce a single best pose hypothesis. In this work, we propose a probabilistic framework that for a given image predicts the arbitrarily shaped posterior distribution of its camera pose. We do this via a novel formulation of camera pose regression using variational inference, which allows sampling from the predicted distribution. Our method outperforms existing methods on localization in ambiguous scenes. We open-source our approach and share our recorded data sequence at github.com/efreidun/vapor.