
🔥人工智能
笔记和资料,涉及到深度学习、自动驾驶等领域。
🔥机器人
包括ROS机器人框架笔记。Beginer Friendly

✅Python教程
从0到1,在深入人工智能的全套Python笔记。

❤️经验经历
过往的感悟和思考。发病日记。

✨碎片技术
学习工作中遇到的很赞的技术碎片,整理好了。

✨学习积累
相对于碎片技术的,已经沉淀为自己的资本的内容。
Paper Reading List
Helpful Materials: GitHub repo
https://github.com/ramdrop/cue
https://github.com/NVIDIA/MinkowskiEngine
【思考】创新点子
65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa951388d187066e6a12bd1c6d157f10db3adecc89270ab26a17b62b33adfe35a600ef14bcc92c15ac3a36355bc651ac1116d8b76dabf93abe7ed14183ac75daaf6fc1be0700cfd2178ea55d6309c8341eea0e9050f79c2b46c671b2dba154a73482ff830171670aba95110b17b417dddd39116bd91aa8c54c9c83b751e9c5b0641d58adfae255c3f17f3c0dc8edc16ce545041c165e318ca75ecfe7882b1a103a5663def4b1af7c27b5a52334405fc0427dc6b66e0d6cc1f20734e2174e0f2f243562f8740f2d45908ae4912f78220c1dcad40f07d63adaa9fea ...
【思考】其他思考
65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa95dee07c63ee55b1eb7d727a3289677f4e6c7d915b8bb775ffe6f17610d75e729003d062c9929b5d7e2b2357d49e5017821c4a11b0da24150bb4470a4e6c4e31cd18e1532e3b26c4f331afe0aa816028e7ea886ad2178c547f9b634979c3cf99d538999ef6b6cc13e13e4467724aeaad00e44438048694d4244e758842624aa2219b354d29b2cc31e8014dbdccd278702c30fa6d796f2b864434c7909157cb71726c0454bae0fa840538502e50ab908152751e141c8cc2acbc1daa9ac8191a632917fa275c11b6c5466aef8a8dad0a8255e761cecbb6669d0c2 ...
【思考】核心思考
65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa953ddf2337fef7e8935e7f6faf9d9e071ac3cb5cfd8a6a29534f7778efa6a511c8fccceb9b420be6b9286cc5b475cc232ac9c1dc968eb881fafd7baadefd30bfbce8e88068fec97fb003fbe6446cac9668ee7124e7239ed2224d1469d4be982454e51590022664b433e5eb55598b4ae2905b17eb80290120c011b2d642b9c86c70fdb896829f9df65e359e06ada9482ce8f37d3fc003a4b7227a8ed7234578d849a779fedcd81a538b6e4e2a19fe572f27ee068585dc84bb254a093c8e9d564a0d411f1a85228c937fa8b5f85a53497acd16f12fcebb24a165c ...
SP Module 10 Connected Speech & HMM Training
From subword units to n-grams: hierarchy of modelsDefining a hierarchy of models: we can compile different HMMs to create models of utterances
We can do some pruning, remove some tokens while proceeding, reduce computation cost (Maybe Heuristic is also can be helpful in such case.)
Conditional independence and the forward algorithmWe use the Markov property of HMMs (i.e. conditional independence assumptions) to make computing probabilities of observation sequences easier
HMM tra ...
SP Module 9 the Hidden Markov Model
Hidden Markov Models for ASRIntro to Hidden Markov Models, comparison to DTW.
dynamic time warping (DTW)
Hidden state sequences and alignmentHidden state sequence, Trellis (i.e. lattice) representation of an HMM, aligning observations to states
grid and lattice
The Viterbi algorithm and token passingThe Viterbi algorithm can be computed on different data structures. The token passing version turns out to be very convenient for ASR.Tthese two different implementations are simply two different w ...
SP Module 8 Feature Engineering
Gaussian distributions in modelsClassification model
If features are highly correlate with each other, we can solve this correlation by rotating the axis, by PCA.
Gaussian distribution of classification result of feature vector
Decision boundary
Cepstral Analysis, Mel-FilterbanksWe now start thinking about what a good representation of the acoustic signal should be, motivating the use Mel-Frequency Cepstral Coefficients (MFCCs).
Since the feature in a feature vector is correlated, if we want to ...
MOB LEC12 Motion Planning
Mission, scenarios and behaviorsTask: Navigate the robot itself from the current position to final destination on the map, without human intervention.
Goal: find most efficient path (trajectory) in terms of time or distance travelled.
Example Common Behavior Sets
Speed tracking
Deceleration to stop
Stay stopped
Yield
Emergency stop
Motion planning constraints
Read more about vehicle dynamic.
Objective functions in planning
Supplementary Readings
Motion Planning For Au ...
SP Module 7 Pattern Matching
Cochlea, Mel-Scale, FilterbanksFrom human speech perception to considerations for features for automatic speech recognition
CochleaDifferent places along the cochlea respond to the incoming frequency.
Mel scaleNonlinearity in hertz scale, linear in mal scale, for cochlea.
Filter banksSimplify of cochlea is like a bank of bandpass filters.lower frequency limit and higher frequency limit.
Wider and wider in higher frequency. triangular filters is more appropriate than the rectangle one sho ...
SP Module 6 Prosody
Connected and Citation SpeechConnected speech differs from the citation form.
Connected Speech ProcessesConnected speech forms are highly variable as the result of a number of processes that apply to consonants and vowels.
Prosodic StructureProsody is the combination of speech properties that break speech into units of time, indicate the boundaries of those units, and highlight certain constituents.
A constituent is a word or a group of words that function as a single unit ...
SP Modules Review Contents (2)
Module 5 TTS front-end
We want to generate speech that is
Intelligible: you can clearly perceive what words are being said
Natural: sounds like human speech
Appropriate: conveys the right meaning in a specific context
Front-end: Analyze text, generate a linguistic specification of what to actually generate
Front-end purpose: derive a linguistic specification from text that includes the necessary information to generate speech
Back-end: Waveform generation from the linguistic specification
...
MOB LEC11 Mapping and Occupancy Grid
Occupancy grid
Occupancy Map Calculus
Practicle issues of Occupancy map
Inverse Measurement Model
Downsampling for lidar
Other Type of Map
Supplementary Readings
Note of Occupancy Maps. (MUST READ)
Lanelets: Efficient Map Representation for Autonomous Driving. (Optional)
Probabilistic robotics. Read Chapter 9 - Occupancy Grid Mapping for an overview of how occupancy grids are generated
Origin: Dr. Chris Lu (Homepage)Translate + Edit: YangSier (Homepage)
:four_leaf_clover:碎碎念:f ...
MOB LEC10 LIDAR, Point Cloud and Iterative Closest Points
LiDAR
LiDAR calculus
State Estimation via Point Set RegressionProblem define
ICP Algorithm
Origin: Dr. Chris Lu (Homepage)Translate + Edit: YangSier (Homepage)
:four_leaf_clover:碎碎念:four_leaf_clover:Hello米娜桑,这里是英国留学中的杨丝儿。我的博客的关键词集中在编程、算法、机器人、人工智能、数学等等,点个关注吧,持续高质量输出中。:cherry_blossom:唠嗑QQ群:兔叽的魔术工房 (942848525):star:B站账号:白拾Official(活跃于知识区和动画区)
MOB LEC9 Reference Frames and GPS
The coordinate systems in mobile robotics
world coordinate system
ego-vehicle coordinate system
Rigid Body AssumptionRigid Body is a solid body in which deformation is zero or so small it can be neglected.
rigid body assumption implied that movement of a sensor mounted on the robot should be the same as other co-located sensors and the whole platform.
Motion in generalMotion that can be described by a rotation and translation. There are 6 degree of freedom (DoF) in 3D space for rigid body.
...