We propose UnLoc, an unsupervised indoor localization scheme that bypasses the need for war-driving. Our key observation is that certain locations in an indoor environment present identifiable signatures on one or more sensing dimensions. An elevator, for instance, imposes a distinct pattern on a smartphone's accelerometer; a corridor-corner may overhear a unique set of WiFi access points; a specific spot may experience an unusual magnetic fluctuation. We hypothesize that these kind of signatures naturally exist in the environment, and can be envisioned as internal landmarks of a building. Mobile devices that "sense" these landmarks can recalibrate their locations, while dead-reckoning schemes can track them between landmarks. Results from 3 different indoor settings, including a shopping mall, demonstrate median location errors of 1:69m. War-driving is not necessary, neither are floorplans the system simultaneously computes the locations of users and landmarks, in a manner that they converge reasonably quickly. We believe this is an unconventional approach to indoor localization, holding promise for real-world deployment.
Imagine a user typing on a laptop keyboard while wearing a smart watch. This paper asks whether motion sensors from the watch can leak information about what the user is typing. While its not surprising that some information will be leaked, the question is how much? We find that when motion signal processing is combined with patterns in English language, the leakage is substantial. Reported results show that when a user types a word $W$, it is possible to shortlist a median of 24 words, such that $W$ is in this shortlist. When the word is longer than $6$ characters, the median shortlist drops to $10$. Of course, such leaks happen without requiring any training from the user, and also under the (obvious) condition that the watch is only on the left hand. We believe this is surprising and merits awareness, especially in light of various continuous sensing apps that are emerging in the app market. Moreover, we discover additional "leaks" that can further reduce the shortlist -- we leave these exploitations to future work.
14 September 2015 in IEEE Transactions on Mobile Computing
Indoor localization using mobile sensors has gained momentum lately. Most of the current systems rely on an extensive calibration step to achieve high accuracy. We propose SemanticSLAM, a novel unsupervised indoor localization scheme that bypasses the need for war-driving. SemanticSLAM leverages the idea that certain locations in an indoor environment have a unique signature on one or more phone sensors. Climbing stairs, for example, has a distinct pattern on the phone's accelerometer; a specific spot may experience an unusual magnetic interference while another may have a unique set of Wi-Fi access points covering it. SemanticSLAM uses these unique points in the environment as landmarks and combines them with dead-reckoning in a new Simultaneous Localization And Mapping (SLAM) framework to reduce both the localization error and convergence time. In particular, the phone inertial sensors are used to keep track of the user's path, while the observed landmarks are used to compensate for the accumulation of error in a unified probabilistic framework. Evaluation in two testbeds on Android phones shows that the system can achieve 0.53 meters human median localization errors. In addition, the system can detect the location of landmarks with 0.83 meters median error. This is 62 percent better than a system that does not use SLAM. Moreover, SemanticSLAM has a 33 percent lower convergence time compared to the same systems. This highlights the promise of SemanticSLAM as an unconventional approach for indoor localization.
This paper aims to track the 3D posture of the entire arm - both wrist and elbow - using the motion and magnetic sensors on smartwatches. We do not intend to employ machine learning to train the system on a specific set of gestures. Instead, we aim to trace the geometric motion of the arm, which can then be used as a generic platform for gesture-based applications. The problem is challenging because the arm posture is a function of both elbow and shoulder motions, whereas the watch is only a single point of (noisy) measurement from the wrist. Moreover, while other tracking systems (like indoor/outdoor localization) often benefit from maps or landmarks to occasionally reset their estimates, such opportunities are almost absent here. While this appears to be an under-constrained problem, we find that the pointing direction of the forearm is strongly coupled to the arm's posture. If the gyroscope and compass on the watch can be made to estimate this direction, the 3D search space can become smaller; the IMU sensors can then be applied to mitigate the remaining uncertainty. We leverage this observation to design ArmTrak, a system that fuses the IMU sensors and the anatomy of arm joints into a modified hidden Markov model (HMM) to continuously estimate state variables. Using Kinect 2.0 as ground truth, we achieve around 9.2 cm of median error for free-form postures; the errors increase to 13.3 cm for a real time version. We believe this is a step forward in posture tracking, and with some additional work, could become a generic underlay to various practical applications.
This paper describes WalkCompass, a system that exploits smartphone sensors to estimate the direction in which a user is walking. We find that several smartphone localization systems in the recent past, including our own, make a simplifying assumption that the user's walking direction is known. In trying to relax this assumption, we were not able to find a generic solution from past work. While intuition suggests that the walking direction should be detectable through the accelerometer, in reality this direction gets blended into various other motion patterns during the act of walking, including up and down bounce, side-to-side sway, swing of arms or legs, etc. Moreover, the walking direction is in the phone's local coordinate system (e.g., along Y axis), and translation to global directions, such as 45 degree North, can be challenging when the compass is itself erroneous. WalkCompass copes with these challenges and develops a stable technique to estimate the user's walking direction within a few steps. Results drawn from 15 different environments demonstrate median error of less than 8 degrees, across 6 different users, 3 surfaces, and 3 holding positions. While there is room for improvement, we believe our current system can be immediately useful to various applications centered around localization and human activity recognition.